Mrinmaya Sachan

Publication Activity (10 Years)

Years Active: 2011-2024
Publications (10 Years): 145

Top Venues

CoRR

EMNLP

ACL (1)

EMNLP (Findings)

Publications

Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals. CoRR (2024)
Andreas Opedal, Alessandro Stolfo, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan
Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? CoRR (2024)
Jingwei Ni, Minjing Shi, Dominik Stammbach, Mrinmaya Sachan, Elliott Ash, Markus Leippold
AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators. CoRR (2024)
Sankalan Pal Chowdhury, Vilém Zouhar, Mrinmaya Sachan
Scaling the Authoring of AutoTutors with Large Language Models. CoRR (2024)
Fernando Gonzalez, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan, Rada Mihalcea
Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good. CoRR (2023)
Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych, Edoardo M. Ponti
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation. CoRR (2023)
Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Ryan Cotterell
All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations. CoRR (2023)
Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan, Elliott Ash
Revisiting Automated Topic Model Evaluation with Large Language Models. EMNLP (2023)
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
Membership Inference Attacks against Language Models via Neighbourhood Comparison. ACL (Findings) (2023)
Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models. EMNLP (2023)
Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models. CoRR (2023)
David F. Jenny, Yann Billeter, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin
Navigating the Ocean of Biases: Political Bias Attribution in Language Models via Causal Structures. CoRR (2023)
Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Mrinmaya Sachan, Ryan Cotterell
Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels. ACL (1) (2023)
Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models. ACL (1) (2023)
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Mrinmaya Sachan, Ryan Cotterell
Tokenization and the Noiseless Channel. ACL (1) (2023)
Tianyu Liu, Afra Amini, Mrinmaya Sachan, Ryan Cotterell
Learning the String Partial Order. CoRR (2023)
Jakub Macina, Nico Daheim, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
Opportunities and Challenges in Neural Dialog Tutoring. EACL (2023)
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Mrinmaya Sachan, Ryan Cotterell
Tokenization and the Noiseless Channel. CoRR (2023)
Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan, Elliott Ash
Re-visiting Automated Topic Model Evaluation with Large Language Models. CoRR (2023)
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Tim Vieira, Mrinmaya Sachan, Ryan Cotterell
A Formal Perspective on Byte-Pair Encoding. CoRR (2023)
Fernando Gonzalez Adauto, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan, Rada Mihalcea
Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good. EMNLP (Findings) (2023)
Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng, Kam-Fai Wong
Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation. CoRR (2023)
Jingwei Ni, Zhijing Jin, Qian Wang, Mrinmaya Sachan, Markus Leippold
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP. CoRR (2023)
Furui Cheng, Vilém Zouhar, Simran Arora, Mrinmaya Sachan, Hendrik Strobelt, Mennatallah El-Assady
RELIC: Investigating Large Language Model Responses using Self-Consistency. CoRR (2023)
Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum, Mrinmaya Sachan
Longtonotes: OntoNotes with Longer Coreference Chains. EACL (Findings) (2023)
Mattia Atzeni, Mrinmaya Sachan, Andreas Loukas
Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning. CoRR (2023)
Shehzaad Dhuliawala, Vilém Zouhar, Mennatallah El-Assady, Mrinmaya Sachan
A Diachronic Perspective on User Trust in AI under Uncertainty. CoRR (2023)
Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng, Kam-Fai Wong
Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation. EACL (Findings) (2023)
Jingwei Ni, Zhijing Jin, Qian Wang, Mrinmaya Sachan, Markus Leippold
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP. ACL (1) (2023)
Alessandro Stolfo, Yonatan Belinkov, Mrinmaya Sachan
A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis. EMNLP (2023)
Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell, Mrinmaya Sachan
RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text. CoRR (2023)
Janvijay Singh, Vilém Zouhar, Mrinmaya Sachan
Enhancing Textbooks with Visuals from the Web for Improved Learning. EMNLP (2023)
Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf
CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models. CoRR (2023)
Vilém Zouhar, Kalvin Chang, Chenxuan Cui, Nathaniel Carlson, Nathaniel Robinson, Mrinmaya Sachan, David R. Mortensen
PWESuite: Phonetic Word Embeddings and Tasks They Facilitate. CoRR (2023)
Ying Jiao, Kumar Shridhar, Peng Cui, Wangchunshu Zhou, Mrinmaya Sachan
Automatic Educational Question Generation with Difficulty Level Controls. AIED (2023)
Andreas Opedal, Niklas Stoehr, Abulhair Saparov, Mrinmaya Sachan
World Models for Math Story Problems. CoRR (2023)
Kumar Shridhar, Alessandro Stolfo, Mrinmaya Sachan
Distilling Reasoning Capabilities into Smaller Language Models. ACL (Findings) (2023)
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi, Li Du, Tim Vieira, Mrinmaya Sachan, Ryan Cotterell
A Formal Perspective on Byte-Pair Encoding. ACL (Findings) (2023)
Kumar Shridhar, Koustuv Sinha, Andrew Cohen, Tianlu Wang, Ping Yu, Ram Pasunuru, Mrinmaya Sachan, Jason Weston, Asli Celikyilmaz
The ART of LLM Refinement: Ask, Refine, and Trust. CoRR (2023)
Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona T. Diab, Bernhard Schölkopf
Can Large Language Models Infer Causation from Correlation? CoRR (2023)
Zeming Liu, Ping Nie, Jie Cai, Haifeng Wang, Zheng-Yu Niu, Peng Zhang, Mrinmaya Sachan, Kaiping Peng
XDailyDialog: A Multilingual Parallel Dialogue Corpus. ACL (1) (2023)
Ishan Kumar, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Negar Kiyavash, Mrinmaya Sachan, Bernhard Schölkopf
CausalCite: A Causal Formulation of Paper Citations. CoRR (2023)
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference. EACL (2023)
Jakub Macina, Nico Daheim, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
Opportunities and Challenges in Neural Dialog Tutoring. CoRR (2023)
Ruida Wang, Wangchunshu Zhou, Mrinmaya Sachan
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models. CoRR (2023)
Janvijay Singh, Vilém Zouhar, Mrinmaya Sachan
Enhancing Textbooks with Visuals from the Web for Improved Learning. CoRR (2023)
Peng Cui, Mrinmaya Sachan
Adaptive and Personalized Exercise Generation for Online Language Learning. CoRR (2023)
Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell, Mrinmaya Sachan
Controlled Text Generation with Natural Language Instructions. CoRR (2023)
Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference. CoRR (2023)
Wangchunshu Zhou, Yuchen Eleanor Jiang, Ryan Cotterell, Mrinmaya Sachan
Efficient Prompting via Dynamic In-Context Learning. CoRR (2023)
Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems. EMNLP (Findings) (2023)
Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell, Mrinmaya Sachan
Controlled Text Generation with Natural Language Instructions. ICML (2023)
Wangchunshu Zhou, Yuchen Eleanor Jiang, Long Li, Jialong Wu, Tiannan Wang, Shi Qiu, Jintian Zhang, Jing Chen, Ruipu Wu, Shuai Wang, Shiding Zhu, Jiyu Chen, Wentao Zhang, Ningyu Zhang, Huajun Chen, Peng Cui, Mrinmaya Sachan
Agents: An Open-source Framework for Autonomous Language Agents. CoRR (2023)
Peng Cui, Mrinmaya Sachan
Adaptive and Personalized Exercise Generation for Online Language Learning. ACL (1) (2023)
Shehzaad Dhuliawala, Mrinmaya Sachan, Carl Allen
Variational Classification. CoRR (2023)
Alessandro Stolfo, Yonatan Belinkov, Mrinmaya Sachan
Understanding Arithmetic Reasoning in Language Models using Causal Mediation Analysis. CoRR (2023)
Zhiheng Lyu, Zhijing Jin, Justus Mattern, Rada Mihalcea, Mrinmaya Sachan, Bernhard Schölkopf
Psychologically-Inspired Causal Prompts. CoRR (2023)
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
Membership Inference Attacks against Language Models via Neighbourhood Comparison. CoRR (2023)
Andreas Opedal, Niklas Stoehr, Abulhair Saparov, Mrinmaya Sachan
World Models for Math Story Problems. ACL (Findings) (2023)
Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf
CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models. NeurIPS (2023)
Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Mrinmaya Sachan, Ryan Cotterell
Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus. CoRR (2023)
Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems. CoRR (2023)
Mattia Atzeni, Mrinmaya Sachan, Andreas Loukas
Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning. ICML (2023)
Shehzaad Dhuliawala, Vilém Zouhar, Mennatallah El-Assady, Mrinmaya Sachan
A Diachronic Perspective on User Trust in AI under Uncertainty. EMNLP (2023)
Tianyu Liu, Afra Amini, Mrinmaya Sachan, Ryan Cotterell
Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective. EMNLP (2023)
Ruida Wang, Wangchunshu Zhou, Mrinmaya Sachan
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models. EMNLP (Findings) (2023)
Kumar Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha, Manu Kapur, Mrinmaya Sachan
Automatic Generation of Socratic Subquestions for Teaching Math Word Problems. CoRR (2022)
Zhijing Jin, Sydney Levine, Fernando Gonzalez, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan, Rada Mihalcea, Josh Tenenbaum, Bernhard Schölkopf
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment. CoRR (2022)
Tianyu Liu, Yuchen Eleanor Jiang, Ryan Cotterell, Mrinmaya Sachan
A Structured Span Selector. NAACL-HLT (2022)
Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Mrinmaya Sachan, Ryan Cotterell
A Bilingual Parallel Corpus with Discourse Annotations. CoRR (2022)
Yu Fei, Ping Nie, Zhao Meng, Roger Wattenhofer, Mrinmaya Sachan
Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations. CoRR (2022)
Daphna Keidar, Andreas Opedal, Zhijing Jin, Mrinmaya Sachan
Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang. CoRR (2022)
Yuchen Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Ryan Cotterell, Mrinmaya Sachan, Ming Zhou
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation. NAACL-HLT (2022)
Daphna Keidar, Andreas Opedal, Zhijing Jin, Mrinmaya Sachan
Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang. ACL (1) (2022)
Kumar Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha, Manu Kapur, Mrinmaya Sachan
Automatic Generation of Socratic Subquestions for Teaching Math Word Problems. EMNLP (2022)
Shehzaad Dhuliawala, Leonard Adolphs, Rajarshi Das, Mrinmaya Sachan
Calibration of Machine Reading Systems at Scale. CoRR (2022)
Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schölkopf, Mrinmaya Sachan
Differentially Private Language Models for Secure Data Sharing. CoRR (2022)
Yuchen Eleanor Jiang, Ryan Cotterell, Mrinmaya Sachan
Investigating the Role of Centering Theory in the Context of Neural Coreference Resolution Systems. CoRR (2022)
Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf
Logical Fallacy Detection. CoRR (2022)
Tianyu Liu, Yuchen Eleanor Jiang, Nicholas Monath, Ryan Cotterell, Mrinmaya Sachan
Autoregressive Structured Prediction with Language Models. EMNLP (Findings) (2022)
Justus Mattern, Zhijing Jin, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf
Understanding Stereotypes in Language Models: Towards Robust Measurement and Zero-Shot Debiasing. CoRR (2022)
Vikram Gupta, Haoyue Shi, Kevin Gimpel, Mrinmaya Sachan
Deep Clustering of Text Representations for Supervision-Free Probing of Syntax. AAAI (2022)
Jiaoda Li, Ryan Cotterell, Mrinmaya Sachan
Probing via Prompting. CoRR (2022)
Yifan Hou, Guoji Fu, Mrinmaya Sachan
Understanding Knowledge Integration in Language Models with Graph Convolutions. CoRR (2022)
Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum, Mrinmaya Sachan
Longtonotes: OntoNotes with Longer Coreference Chains. CoRR (2022)
Tianyu Liu, Yuchen Jiang, Nicholas Monath, Ryan Cotterell, Mrinmaya Sachan
Autoregressive Structured Prediction with Language Models. CoRR (2022)
Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models. CoRR (2022)
Yifan Hou, Guoji Fu, Mrinmaya Sachan
What Has Been Enhanced in my Knowledge-Enhanced Language Model? EMNLP (Findings) (2022)
Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu, Mrinmaya Sachan
Adapters for Enhanced Modeling of Multilingual Knowledge and Text. EMNLP (Findings) (2022)
Zhijing Jin, Sydney Levine, Fernando Gonzalez Adauto, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan, Rada Mihalcea, Josh Tenenbaum, Bernhard Schölkopf
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment. NeurIPS (2022)
Shehzaad Dhuliawala, Leonard Adolphs, Rajarshi Das, Mrinmaya Sachan
Calibration of Machine Reading Systems at Scale. ACL (Findings) (2022)
Kumar Shridhar, Alessandro Stolfo, Mrinmaya Sachan
Distilling Multi-Step Reasoning Capabilities of Large Language Models into Smaller Models via Semantic Decompositions. CoRR (2022)
Zhao Meng, Yihan Dong, Mrinmaya Sachan, Roger Wattenhofer
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks. NAACL-HLT (Findings) (2022)
Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu, Mrinmaya Sachan
Adapters for Enhanced Modeling of Multilingual Knowledge and Text. CoRR (2022)
Yu Fei, Zhao Meng, Ping Nie, Roger Wattenhofer, Mrinmaya Sachan
Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations. EMNLP (2022)
Mattia Atzeni, Shehzaad Zuzar Dhuliawala, Keerthiram Murugesan, Mrinmaya Sachan
Case-based reasoning for better generalization in textual reinforcement learning. ICLR (2022)
Jingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan, Bernhard Schölkopf
Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance. NAACL-HLT (2022)
Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schölkopf, Mrinmaya Sachan
Differentially Private Language Models for Secure Data Sharing. EMNLP (2022)
Tianyu Liu, Yuchen Eleanor Jiang, Ryan Cotterell, Mrinmaya Sachan
A Structured Span Selector. CoRR (2022)
Alessandro Stolfo, Chris Tanner, Vikram Gupta, Mrinmaya Sachan
A Simple Unsupervised Approach for Coreference Resolution using Rule-based Weak Supervision. *SEM@NAACL-HLT (2022)

Mrinmaya Sachan.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Mrinmaya Sachan