Alert button
Picture for Mrinmaya Sachan

Mrinmaya Sachan

Alert button

Scaling the Authoring of AutoTutors with Large Language Models

Feb 14, 2024
Sankalan Pal Chowdhury, Vilém Zouhar, Mrinmaya Sachan

Viaarxiv icon

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Jan 31, 2024
Andreas Opedal, Alessandro Stolfo, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan

Viaarxiv icon

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

Dec 07, 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

Viaarxiv icon

RELIC: Investigating Large Language Model Responses using Self-Consistency

Nov 28, 2023
Furui Cheng, Vilém Zouhar, Simran Arora, Mrinmaya Sachan, Hendrik Strobelt, Mennatallah El-Assady

Viaarxiv icon

Navigating the Ocean of Biases: Political Bias Attribution in Language Models via Causal Structures

Nov 15, 2023
David F. Jenny, Yann Billeter, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin

Viaarxiv icon

The ART of LLM Refinement: Ask, Refine, and Trust

Nov 14, 2023
Kumar Shridhar, Koustuv Sinha, Andrew Cohen, Tianlu Wang, Ping Yu, Ram Pasunuru, Mrinmaya Sachan, Jason Weston, Asli Celikyilmaz

Viaarxiv icon

CausalCite: A Causal Formulation of Paper Citations

Nov 05, 2023
Ishan Kumar, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Negar Kiyavash, Mrinmaya Sachan, Bernhard Schoelkopf

Viaarxiv icon

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

Oct 23, 2023
Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan

Viaarxiv icon

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

Oct 20, 2023
Ruida Wang, Wangchunshu Zhou, Mrinmaya Sachan

Viaarxiv icon

A Diachronic Perspective on User Trust in AI under Uncertainty

Oct 20, 2023
Shehzaad Dhuliawala, Vilém Zouhar, Mennatallah El-Assady, Mrinmaya Sachan

Viaarxiv icon