Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena

Jiangjie ChenSiyu YuanRong YeKyle RichardsonKyle Richardson
2023
arXiv

Can Large Language Models (LLMs) simulate human behavior in complex environments? LLMs have recently been shown to exhibit advanced reasoning skills but much of NLP evaluation still relies on static… 

Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations

Nirbhay ModheQiaozi GaoA. KalyanG. Sukhatme
2023
arXiv.org

Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free… 

DISCO: Distilling Phrasal Counterfactuals with Large Language Models

Zeming ChenQiyue GaoKyle RichardsonAshish Sabharwal
2023
ACL

Recent methods demonstrate that data augmentation using counterfactual knowledge can teach models the causal structure of a task, leading to robust and generalizable models. However, such… 

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Harsh TrivediNiranjan BalasubramanianTushar KhotAshish Sabharwal
2023
ACL

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They… 

Do language models have coherent mental models of everyday things?

Yuling GuBhavana Dalvi MishraPeter Clark
2023
ACL

When people think of everyday things like an “egg,” they typically have a mental image associated with it. This commonsense knowledge helps us understand how these everyday things work and how to… 

RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs

Afra Feyza AkyurekEkin AkyürekAman MadaanNiket Tandon
2023
Annual Meeting of the Association for Computational Linguistics

Despite their unprecedented success, even the largest language models make mistakes.Similar to how humans learn and improve using feedback, previous work proposed providing language models with… 

Let Me Teach You: Pedagogical Foundations of Feedback for Language Models

Beatriz BorgesNiket TandonTanja KaserAntoine Bosselut
2023
arXiv

Natural Language Feedback (NLF) is an increasingly popular avenue to align Large Language Models (LLMs) to human preferences. Despite the richness and diversity of the information it can convey, NLF… 

Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance

Yao FuLitu OuMingyu ChenTushar Khot
2023
ICML 2023, the Challenges in Deployable Generative AI workshop

As large language models (LLMs) are continuously being developed, their evaluation becomes increasingly important yet challenging. This work proposes Chain-of-Thought Hub, an open-source evaluation… 

The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks

Nikil SelvamSunipa DevDaniel KhashabiKai-Wei Chang
2023
ACL

How reliably can we trust the scores obtained from social bias benchmarks as faithful indicators of problematic social biases in a given language model? In this work, we study this question by… 

Aligning Language Models to User Opinions

EunJeong HwangBodhisattwa Prasad MajumderNiket Tandon
2023
arXiv

An important aspect of developing LLMs that interact with humans is to align models' behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user…