Publications

Group highlights

More resources can be found here.

(For a full list see below or go to Google Scholar)

A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis

We explore a mechanistic interpretation of LMs for arithmetic reasoning tasks using causal mediation analysis.

Alessandro Stolfo, Yonatan Belinkov and Mrinmaya Sachan

EMNLP 2023    

MATHDIAL: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems

We propose an approach to semi-synthetically generate a pedagogically rich dialog dataset by pairing real teachers with a large language models scaffolded to represent common student errors.

Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha, Manu Kapur, Iryna Gurevych and Mrinmaya Sachan

EMNLP 2023 (Findings)   Code  

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

We explore a mechanistic interpretation of LMs for multi-step reasoning tasks.

Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut and Mrinmaya Sachan

EMNLP 2023    

Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models

We propose a data synthesis approach that iteratively extrapolates errors made by a small model trained on the synthesized dataset on a real-world validation dataset using LLMs.

Ruida Wang, Wangchunshu Zhou and Mrinmaya Sachan

EMNLP 2023 (Findings)    

Re-visiting Automated Topic Model Evaluation with Large Language Models

We study how topic models can be automatically evaluated using LLMs.

Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan and Elliott Ash

EMNLP 2023 (Short)    

A Diachronic Perspective on User Trust in AI under Uncertainty

We study how user trust is developed and how it can be regained after potential trust-eroding events in Human-AI collaboration.

Shehzaad Dhuliawala, Vilém Zouhar, Mennatallah El-Assady and Mrinmaya Sachan

EMNLP 2023    

Can Large Language Models Infer Causation from Correlation?

We propose a benchmark dataset to test the pure causal inference skills of large language models (LLMs) and identify a key shortcoming of LLMs in terms of their causal inference skills.

Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona Diab and Bernhard Schölkopf

arXiv 2023    

CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models

We propose a new NLP task, causal inference in natural language, inspired by the “causal inference engine” postulated by Judea Pearl et al.

Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng LYU, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan and Bernhard Schölkopf

NeurIPS 2023    

Order-Theoretic Structured Prediction: Partially Ordering Tokens within a String

We reduce the complexity of structure prediction tasks to linear by casting the relation between tokens as a partial order over the string.

Tianyu Liu, Afra Amini, Mrinmaya Sachan and Ryan Cotterell

EMNLP 2023 (Outstanding Paper Award)    

RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

We present RecurrentGPT, a language based simulacrum of the recurrence mechanism in RNNs which enables us to use ChatGPT to generate long texts.

Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell and Mrinmaya Sachan

arXiv 2023    

Efficient Prompting via Dynamic In-Context Learning

We propose DYNAICL, a recipe for efficient prompting with black-box generalist models that dynamically allocate in-context examples according to the input complexity and the computational budget.

Wangchunshu Zhou, Yuchen Eleanor Jiang, Ryan Cotterell and Mrinmaya Sachan

arXiv 2023    

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good

We introduce NLP4SGPAPERS, a scientific dataset with three associated tasks that can help identify NLP for social good (NLP4SG) papers and characterize the NLP4SG landscape.

Fernando Gonzalez, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan and Rada Mihalcea

EMNLP 2023 (Findings)    

Enhancing Textbooks with Visuals from the Web for Improved Learning

We propose a vision-language model based approach to automatically enhance textbooks with images from the web.

Janvijay Singh, Vilém Zouhar and Mrinmaya Sachan

EMNLP 2023    

Elastic Weight Removal for Faithful and Abstractive Dialogue Generation

We propose a new approach for mitigating hallucination or generation of unverifiable information in dialog models

Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych and Edoardo M Ponti

arxiv:2303.17574    

Adaptive and Personalized Exercise Generation for Online Language Learning

We combine a knowledge tracing model that estimates each student’s evolving knowledge states from their learning history and a controlled text generation model that generates exercises based on the student’s current estimated knowledge state and instructor requirements of desired properties for the next exercise.

Peng Cui and Mrinmaya Sachan

ACL 2023    

A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models

We propose a causal framework to quantify the robustness of the reasoning abilities of language models.

Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf and Mrinmaya Sachan

ACL 2023 (also at MATHAI Workshop at NeurIPS 22)    

Distilling Reasoning Capabilities into Smaller Language Models

We propose a knowledge distillation framework that leverages step-by-step reasoning capabilities of larger models and distills these capabilities into smaller models.

Kumar Shridhar, Alessandro Stolfo and Mrinmaya Sachan

ACL 2023 (Findings)    

World Models for Math Story Problems

As a step towards developing interpretable language model reasoners, we develop a semantic formalism representing the world depicted in math story problems.

Andreas Opedal, Niklas Stoehr, Abulhair Saparov and Mrinmaya Sachan

ACL 2023 (Findings)    

Byte-Pair Encoding is Approximately Optimal

We formalize BPE as a combinatorial optimization problem and use submodularity to prove that the iterative greedy approach to BPE is approximately optimal.

Vilém Zouhar, Tim Vieira, Clara Meister, Juan Luis Gastaldi, Mrinmaya Sachan and Ryan Cotterell

ACL 2023 (Findings)    

Controlled Text Generation with Natural Language Instructions

We present InstructCTG, a controlled text generation framework that incorporates different constraints by conditioning the text generation process on natural language descriptions and demonstrations of the constraints.

Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell and Mrinmaya Sachan

ICML 2023    

Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning

We introduce LatFormer, a model that incorporates lattice geometry and topology priors in attention masks for abstract reasoning problems.

Mattia Atzeni, Mrinmaya Sachan and Andreas Loukas

ICML 2023    

Educational Question Generation with Difficulty Level Controls

We automatically generate math word problems of various difficulties that meet the needs of teachers in teaching and testing students in various educational stages.

Ying Jiao, Kumar Shridhar, Peng Cui, Wangchunshu Zhou and Mrinmaya Sachan

AIED 2023    

Opportunities and Challenges in Neural Dialog Tutoring

We analyze the potential of neural models on dialog tutoring datasets for language learning using a suite of automatic and human evaluations.

Jakub Macina, Nico Daheim, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych and Mrinmaya Sachan

EACL 2023   Code  

Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation

We propose a self-distillation approach to jointly predict teaching strategies and generate tutor responses accordingly for dialog tutoring.

Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng and Kam-Fai Wong

EACL 2023 (Short, Findings)    

LongtoNotes: OntoNotes with Longer Coreference Chains

We reconstruct a long document coreference corpus out of Ontonotes, arriving at a more challenging coreference task and dataset.

Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum and Mrinmaya Sachan

EACL 2023 (Findings)    

Automatic Generation of Socratic Subquestions for Teaching Math Word Problems

We use reinforcement learning and language models to generate sequential subquestions for guiding (machines/humans) in math word problem-solving.

Kumar Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha, Manu Kapur and Mrinmaya Sachan

EMNLP 2022 (also at MATHAI Workshop at NeurIPS 22)   Code  

Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

We show that zero-shot text classification can be improved simply by clustering texts in the embedding spaces of LMs.

Yu Fei, Zhao Meng, Ping Nie, Roger Wattenhofer and Mrinmaya Sachan

EMNLP 2022    

Differentially Private Language Models for Secure Data Sharing

We generate synthetic datasets from differentially private LMs as a solution for sharing textual data while protecting the privacy of users.

Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schölkopf and Mrinmaya Sachan

EMNLP 2022    

Autoregressive Structured Prediction with Language Models

We model structures as an autoregressive sequence of actions with LMs and achieve strong results on various sturctured prediction problems.

Tianyu Liu, Yuchen Eleanor Jiang, Nicholas Monath, Ryan Cotterell and Mrinmaya Sachan

EMNLP 2022 (Findings, Short paper)    

Adapters for Enhanced Modeling of Multilingual Knowledge and Text

We enhance multilingual LMs with knowledge from multilingual knowledge graphs to tackle language and knowledge graph tasks across many languages.

Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu and Mrinmaya Sachan

EMNLP 2022 (Findings) / Best paper at the Multilingual Representation Learning (MRL) Workshop    

Logical Fallacy Detection

We introduce a new reasoning task and dataset of Logical fallacy detection.

Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea and Bernhard Schölkopf

EMNLP 2022 (Findings)    

What has been Enhanced in my Knowledge-Enhanced Language Model?

We propose a probe model based on graph convolutions to interpret knowledge-enhanced LMs and understand what kind of knowledge is integrated into these models.

Yifan Hou, Guoji Fu and Mrinmaya Sachan

EMNLP 2022 (Findings)   Code  

Rule-Based but Flexible? Evaluating and Improving Language Models as Accounts of Human Moral Judgment

We present a novel challenge set that highlights the flexibility of the human moral mind, analyze the performance of language models on it, and propose a Moral Chain-of-Thought prompting strategy.

Zhijing Jin, Sydney Levine, Fernando Gonzalez Adauto, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan, Rada Mihalcea, Joshua B. Tenenbaum and Bernhard Schölkopf

NeurIPS 2022 (Oral) / CogSci 2022 (Disciplinary Diversity and Integration Award)    

Learning the Transformer Kernel

We propose kernel learning methods that increase the expressiveness of Efficient Transformers while keeping their complexity linear.

Sankalan Pal Chowdhury, Adamos Solomou, Avinava Dubey and Mrinmaya Sachan

TMLR 2022    

Probing via Prompting

We propose a probing approach that adapts the given task into a sentence completion format and performs probing using the built-in language modeling head.

Jiaoda Li, Ryan Cotterell and Mrinmaya Sachan

NAACL 2022    

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation

We propose a novel automatic metric to widen the scope of automatic MT evaluation from sentence to document level.

Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Mrinmaya Sachan, Ryan Cotterell and Ming Zhou

NAACL 2022    

A Structured Span Selector

We propose a structured model which directly learns to select an optimal set of spans for various span selection problems.

Tianyu Liu, Yuchen Eleanor Jiang, Ryan D Cotterell and Mrinmaya Sachan

NAACL 2022    

Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance

We provide a causal analysis of the impact of translationese on Machine Translation performance.

Jingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan and Bernhard Schölkopf

NAACL 2022    

Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models

We improve BERT’s robustness against word substitution attacks by leveraging self-supervised contrastive learning.

Zhao Meng, Yihan Dong, Mrinmaya Sachan and Roger Wattenhofer

NAACL 2022 (Findings)    

Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang

We study language change through the lens of causality in order to model how various distributional factors causally effect language change

Daphna Keidar, Andreas Opedal, Zhijing Jin and Mrinmaya Sachan

ACL 2022    

Calibration of Machine Reading Systems at Scale

We propose approaches to calibrate open-domain machine reading systems

Shehzaad Dhuliawala, Leonard Adolphs, Rajarshi Das and Mrinmaya Sachan

ACL 2022 (Findings)    

Case-based Reasoning for Better Generalization in Text-Adventure Games

We propose a case-based reasoning approach to train agents and generalize efficiently out of the training distribution.

Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Murugesan and Mrinmaya Sachan

ICLR (2022)    

Deep Clustering of Text Representations for Supervision-free Probing of Syntax

We jointly map contextualized text representations to a lower dimensional space and cluster them for syntax induction.

Vikram Gupta, Haoyue Shi, Kevin Gimpel and Mrinmaya Sachan

AAAI (2022)    

Causal Direction in Data Matters: Implications of Causal and Anticausal Learning in NLP

We investigate role of the process of data collection in NLP and explain it using causality.

Zhijing Jin, Julius von Kugelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan and Bernhard Schoelkopf

EMNLP 2021    

Let Your Characters Tell Their Story: A Dataset for Character-Centric Narrative Understanding

We introduce a dataset for literary pieces and their summaries together with descriptions of characters that appear in the texts.

Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan and Snigdha Chaturvedi

EMNLP 2021 (Findings)    

Differentiable Subset Pruning of Transformer Heads

We introduce a new differentiable subset pruning technique for Transformer head pruning.

Jiaoda Li, Ryan Cotterell and Mrinmaya Sachan

TACL 2021   Code  

Bird's Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach

We introduce a information-theoretic probe to detect if contextualized text representations encode information in linguistic graphs.

Yifan Hou and Mrinmaya Sachan

ACL 2021   Code  

Scaling Within Document Coreference for Long Texts

We introduce a coreference model which scales to documents of any length.

Raghuveer Thirukovalluru, Nicholas Monath, Kumar Shridhar, Manzil Zaheer, Mrinmaya Sachan and Andrew McCallum

ACL 2021 (Findings)    

How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact

We propose thinking frameworks to understand the direct and indirect real-world impact of NLP.

Zhijing Jin, Geeticka Chauhan, Brian Tse, Mrinmaya Sachan and Rada Mihalcea

ACL 2021 (Findings)   MIT News Article  

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

We jointly map contextualized text representations to a lower dimensional space and cluster them for syntax induction.

Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi,Kartik Talamadupula, Mrinmaya Sachan and Murray Campbell

ACL 2021 (Short paper)    

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

We design new environments to test the ability of RL agents to utilize commonsense knowledge.

Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla, Sadhana Kumaravel, Gerald Tesauro, Kartik Talamadupula, Mrinmaya Sachan and Murray Campbell

AAAI 2021    

Discourse in Multimedia: A Case Study in Extracting Geometry Knowledge from Textbooks

We harvest structured knowledge of geometry from math textbooks.

Mrinmaya Sachan, Avinava Dubey, Eduard Hovy, Tom Mitchell, Dan Roth and Eric P. Xing

Computational Linguistics (CL) journal - Dec 2019 issue    

Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems

We learn a pipeline process that incorporates existing code, pre-learned machine learning models, and human engineered rules.

Mrinmaya Sachan, Avinava Dubey, Tom Mitchell, Dan Roth and Eric P. Xing

NeurIPS 2018    

Contextual Parameter Generation for Universal Neural Machine Translation

We propose a meta-learning approach for universal NMT.

Emmanouil Antonios Platanios, Mrinmaya Sachan, Graham Neubig and Tom Mitchell

EMNLP 2018    

Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks

We learn to solve geometry problems by imitation demonstrations in textbooks.

Mrinmaya Sachan and Eric P. Xing

StarSem 2017    

Science Question Answering using Instructional Materials

We propose a structured prediction approach to answer science questions in textbooks.

Mrinmaya Sachan, Avinava Dubey and Eric P. Xing

ACL 2016 (Short paper)    

Machine Comprehension using Rich Semantic Representations

We propose an approach to answer reading comprehension questions using AMR graph representations.

Mrinmaya Sachan and Eric P. Xing

ACL 2016 (Short paper)    

Learning Answer-Entailing Structures for Machine Comprehension

We propose a structured prediction approach to answer reading comprehension questions.

Mrinmaya Sachan, Avinava Dubey, Eric P. Xing and Matthew Richardson

ACL 2015 (Outstanding paper)    

 

Full List

A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis
Alessandro Stolfo, Yonatan Belinkov and Mrinmaya Sachan
EMNLP 2023

MATHDIAL: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems
Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha, Manu Kapur, Iryna Gurevych and Mrinmaya Sachan
EMNLP 2023 (Findings)

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut and Mrinmaya Sachan
EMNLP 2023

Let’s Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
Ruida Wang, Wangchunshu Zhou and Mrinmaya Sachan
EMNLP 2023 (Findings)

Re-visiting Automated Topic Model Evaluation with Large Language Models
Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan and Elliott Ash
EMNLP 2023 (Short)

A Diachronic Perspective on User Trust in AI under Uncertainty
Shehzaad Dhuliawala, Vilém Zouhar, Mennatallah El-Assady and Mrinmaya Sachan
EMNLP 2023

Can Large Language Models Infer Causation from Correlation?
Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona Diab and Bernhard Schölkopf
arXiv 2023

CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models
Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng LYU, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan and Bernhard Schölkopf
NeurIPS 2023

Order-Theoretic Structured Prediction: Partially Ordering Tokens within a String
Tianyu Liu, Afra Amini, Mrinmaya Sachan and Ryan Cotterell
EMNLP 2023 (Outstanding Paper Award)

RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text
Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell and Mrinmaya Sachan
arXiv 2023

Efficient Prompting via Dynamic In-Context Learning
Wangchunshu Zhou, Yuchen Eleanor Jiang, Ryan Cotterell and Mrinmaya Sachan
arXiv 2023

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good
Fernando Gonzalez, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan and Rada Mihalcea
EMNLP 2023 (Findings)

Enhancing Textbooks with Visuals from the Web for Improved Learning
Janvijay Singh, Vilém Zouhar and Mrinmaya Sachan
EMNLP 2023

Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych and Edoardo M Ponti
arxiv:2303.17574

PWESuite: Phonetic Word Embeddings and Tasks They Facilitate
Vilém Zouhar, Kalvin Chang, Chenxuan Cui, Nathaniel Carlson, Nathaniel Robinson, Mrinmaya Sachan and David Mortensen
arxiv:2304.02541

Investigating the Role of Centering Theory in the Context of Neural Coreference Resolution Systems
Yuchen Eleanor Jiang, Ryan Cotterell and Mrinmaya Sachan
arxiv:2210.14678

Adaptive and Personalized Exercise Generation for Online Language Learning
Peng Cui and Mrinmaya Sachan
ACL 2023

A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models
Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf and Mrinmaya Sachan
ACL 2023 (also at MATHAI Workshop at NeurIPS 22)

Distilling Reasoning Capabilities into Smaller Language Models
Kumar Shridhar, Alessandro Stolfo and Mrinmaya Sachan
ACL 2023 (Findings)

World Models for Math Story Problems
Andreas Opedal, Niklas Stoehr, Abulhair Saparov and Mrinmaya Sachan
ACL 2023 (Findings)

Byte-Pair Encoding is Approximately Optimal
Vilém Zouhar, Tim Vieira, Clara Meister, Juan Luis Gastaldi, Mrinmaya Sachan and Ryan Cotterell
ACL 2023 (Findings)

Tokenization and the Noiseless Channel
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Mrinmaya Sachan and Ryan Cotterell
ACL 2023

XDailyDialog: A Multilingual Parallel Dialog Corpus
Zeming Liu, Ping Nie, Jie Cai, Haifeng Wang, Zheng-Yu Niu, Peng Zhang, Mrinmaya Sachan and Kaiping Peng
ACL 2023

When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP
Jingwei Ni, Zhijing Jin, Qian Wang, Mrinmaya Sachan and Markus Leippold
ACL 2023

Discourse-Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus
Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Mrinmaya Sachan and Ryan Cotterell
ACL 2023

Membership Inference Attacks against Language Models via Neighbourhood Comparison
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Scholkopf, Mrinmaya Sachan and Taylor Berg-Kirkpatrick
ACL 2023 (Findings)

Controlled Text Generation with Natural Language Instructions
Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell and Mrinmaya Sachan
ICML 2023

Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning
Mattia Atzeni, Mrinmaya Sachan and Andreas Loukas
ICML 2023

Educational Question Generation with Difficulty Level Controls
Ying Jiao, Kumar Shridhar, Peng Cui, Wangchunshu Zhou and Mrinmaya Sachan
AIED 2023

Opportunities and Challenges in Neural Dialog Tutoring
Jakub Macina, Nico Daheim, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych and Mrinmaya Sachan
EACL 2023

Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation
Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng and Kam-Fai Wong
EACL 2023 (Short, Findings)

Poor Man’s Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang and Mrinmaya Sachan
EACL 2023

LongtoNotes: OntoNotes with Longer Coreference Chains
Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum and Mrinmaya Sachan
EACL 2023 (Findings)

Automatic Generation of Socratic Subquestions for Teaching Math Word Problems
Kumar Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha, Manu Kapur and Mrinmaya Sachan
EMNLP 2022 (also at MATHAI Workshop at NeurIPS 22)

Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations
Yu Fei, Zhao Meng, Ping Nie, Roger Wattenhofer and Mrinmaya Sachan
EMNLP 2022

Differentially Private Language Models for Secure Data Sharing
Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schölkopf and Mrinmaya Sachan
EMNLP 2022

Autoregressive Structured Prediction with Language Models
Tianyu Liu, Yuchen Eleanor Jiang, Nicholas Monath, Ryan Cotterell and Mrinmaya Sachan
EMNLP 2022 (Findings, Short paper)

Adapters for Enhanced Modeling of Multilingual Knowledge and Text
Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu and Mrinmaya Sachan
EMNLP 2022 (Findings) / Best paper at the Multilingual Representation Learning (MRL) Workshop

Logical Fallacy Detection
Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea and Bernhard Schölkopf
EMNLP 2022 (Findings)

What has been Enhanced in my Knowledge-Enhanced Language Model?
Yifan Hou, Guoji Fu and Mrinmaya Sachan
EMNLP 2022 (Findings)

Rule-Based but Flexible? Evaluating and Improving Language Models as Accounts of Human Moral Judgment
Zhijing Jin, Sydney Levine, Fernando Gonzalez Adauto, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan, Rada Mihalcea, Joshua B. Tenenbaum and Bernhard Schölkopf
NeurIPS 2022 (Oral) / CogSci 2022 (Disciplinary Diversity and Integration Award)

Learning the Transformer Kernel
Sankalan Pal Chowdhury, Adamos Solomou, Avinava Dubey and Mrinmaya Sachan
TMLR 2022

Probing via Prompting
Jiaoda Li, Ryan Cotterell and Mrinmaya Sachan
NAACL 2022

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Mrinmaya Sachan, Ryan Cotterell and Ming Zhou
NAACL 2022

A Structured Span Selector
Tianyu Liu, Yuchen Eleanor Jiang, Ryan D Cotterell and Mrinmaya Sachan
NAACL 2022

Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance
Jingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan and Bernhard Schölkopf
NAACL 2022

Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models
Zhao Meng, Yihan Dong, Mrinmaya Sachan and Roger Wattenhofer
NAACL 2022 (Findings)

Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang
Daphna Keidar, Andreas Opedal, Zhijing Jin and Mrinmaya Sachan
ACL 2022

Calibration of Machine Reading Systems at Scale
Shehzaad Dhuliawala, Leonard Adolphs, Rajarshi Das and Mrinmaya Sachan
ACL 2022 (Findings)

Case-based Reasoning for Better Generalization in Text-Adventure Games
Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Murugesan and Mrinmaya Sachan
ICLR (2022)

Deep Clustering of Text Representations for Supervision-free Probing of Syntax
Vikram Gupta, Haoyue Shi, Kevin Gimpel and Mrinmaya Sachan
AAAI (2022)

Causal Direction in Data Matters: Implications of Causal and Anticausal Learning in NLP
Zhijing Jin, Julius von Kugelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan and Bernhard Schoelkopf
EMNLP 2021

Let Your Characters Tell Their Story: A Dataset for Character-Centric Narrative Understanding
Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan and Snigdha Chaturvedi
EMNLP 2021 (Findings)

Differentiable Subset Pruning of Transformer Heads
Jiaoda Li, Ryan Cotterell and Mrinmaya Sachan
TACL 2021

Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach
Yifan Hou and Mrinmaya Sachan
ACL 2021

Scaling Within Document Coreference for Long Texts
Raghuveer Thirukovalluru, Nicholas Monath, Kumar Shridhar, Manzil Zaheer, Mrinmaya Sachan and Andrew McCallum
ACL 2021 (Findings)

How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact
Zhijing Jin, Geeticka Chauhan, Brian Tse, Mrinmaya Sachan and Rada Mihalcea
ACL 2021 (Findings)

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi,Kartik Talamadupula, Mrinmaya Sachan and Murray Campbell
ACL 2021 (Short paper)

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla, Sadhana Kumaravel, Gerald Tesauro, Kartik Talamadupula, Mrinmaya Sachan and Murray Campbell
AAAI 2021

Stronger Transformers for Neural Multi-Hop Question Generation
Devendra Singh Sachan, Lingfei Wu, Mrinmaya Sachan and William Hamilton
arXiv:2010.11374 (2020)

Knowledge Graph Embedding Compression
Mrinmaya Sachan
ACL 2020

Discourse in Multimedia: A Case Study in Extracting Geometry Knowledge from Textbooks
Mrinmaya Sachan, Avinava Dubey, Eduard Hovy, Tom Mitchell, Dan Roth and Eric P. Xing
Computational Linguistics (CL) journal - Dec 2019 issue

Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems
Mrinmaya Sachan, Avinava Dubey, Tom Mitchell, Dan Roth and Eric P. Xing
NeurIPS 2018

Parsing to Programs: A Framework for Situated QA
Mrinmaya Sachan and Eric P. Xing
KDD 2018

Self-Training for Jointly Learning to Ask and Answer Questions
Mrinmaya Sachan and Eric P. Xing
NAACL-HLT 2018

Contextual Parameter Generation for Universal Neural Machine Translation
Emmanouil Antonios Platanios, Mrinmaya Sachan, Graham Neubig and Tom Mitchell
EMNLP 2018

Effective Use of Bidirectional Language Modeling for Medical Named Entity Recognition
Devendra Singh Sachan, Pengtao Xie, Mrinmaya Sachan and Eric P. Xing
MLHC 2018

From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems
Mrinmaya Sachan, Avinava Dubey and Eric P. Xing
EMNLP 2017

Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks
Mrinmaya Sachan and Eric P. Xing
StarSem 2017

Easy Questions First? A Case Study on Curriculum Learning for Question Answering.
Mrinmaya Sachan and Eric P. Xing
ACL 2016

Science Question Answering using Instructional Materials
Mrinmaya Sachan, Avinava Dubey and Eric P. Xing
ACL 2016 (Short paper)

Machine Comprehension using Rich Semantic Representations
Mrinmaya Sachan and Eric P. Xing
ACL 2016 (Short paper)

Learning Concept Taxonomies from Multi-modal Data
Hao Zhang, Zhiting Hu, Yuntian Deng, Mrinmaya Sachan, Zhicheng Yan and Eric P. Xing
ACL 2016

Grounding Topic Models with Knowledge Bases
Zhiting Hu, Gang Luo, Mrinmaya Sachan, Eric P. Xing and Zaiqing Nie
IJCAI 2016

Learning Answer-Entailing Structures for Machine Comprehension
Mrinmaya Sachan, Avinava Dubey, Eric P. Xing and Matthew Richardson
ACL 2015 (Outstanding paper)

An Active Learning Approach to Coreference Resolution.
Mrinmaya Sachan, Eduard H. Hovy and Eric P. Xing
IJCAI 2015