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

A Design Space for Intelligent and Interactive Writing Assistants

Mina LeeKaty Ilonka GeroJohn Joon Young ChungPao Siangliulue
2024
CHI

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge… 

Improving Language Models with Advantage-based Offline Policy Gradients

Ashutosh BahetiXiming LuFaeze BrahmanMark O. Riedl
2024
ICLR

Language Models (LMs) achieve substantial language capabilities when finetuned using Reinforcement Learning with Human Feedback (RLHF). However, RLHF is an unstable and data-hungry process that… 

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

Tom SherborneNaomi SaphraPradeep DasigiHao Peng
2024
ICLR

By reducing the curvature of the loss surface in the parameter space, Sharpness-aware minimization (SAM) yields widespread robustness improvement under domain transfer. Instead of focusing on… 

The Expressive Power of Transformers with Chain of Thought

William MerrillAshish Sabharwal
2024
ICLR

Recent theoretical work has identified surprisingly simple reasoning problems, such as checking if two nodes in a graph are connected or simulating finite-state machines, that are provably… 

What's In My Big Data?

Yanai ElazarAkshita BhagiaIan MagnussonJesse Dodge
2024
ICLR

Large text corpora are the backbone of language models. However, we have a limited understanding of the content of these corpora, including general statistics, quality, social factors, and inclusion… 

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

Shashank GuptaVaishnavi ShrivastavaA. DeshpandeTushar Khot
2024
ICLR

Recent works have showcased the ability of LLMs to embody diverse personas in their responses, exemplified by prompts like 'You are Yoda. Explain the Theory of Relativity.' While this ability allows… 

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Akari AsaiZeqiu WuYizhong WangHannaneh Hajishirzi
2024
ICLR

Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate.… 

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Pan LuHritik BansalTony XiaJianfeng Gao
2024
ICLR

Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in visual contexts… 

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

Sewon MinSuchin GururanganEric WallaceLuke Zettlemoyer
2024
ICLR

The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if trained only on… 

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

Qingqing CaoSewon MinYizhong WangHannaneh Hajishirzi
2024
ICLR

Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is…