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

Ai2 Scholar QA: Organized Literature Synthesis with Attribution

Amanpreet SinghJoseph Chee ChangChloe AnastasiadesSergey Feldman
2025
ACL

Retrieval-augmented generation is increasingly effective in answering scientific questions from literature, but many state-of-the-art systems are expensive and closed-source. We introduce Ai2… 

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

Kevin PuK. FengTovi GrossmanPao Siangliulue
2025
CHI

Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support… 

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference

Mingqi GaoYixin LiuXinyu HuArman Cohan
2025
NAACL

Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. Due to the high cost and time-consuming nature of human… 

Social-RAG: Retrieving from Group Interactions to Socially Ground Proactive AI Generation to Group Preferences

Ruotong WangXinyi ZhouLin QiuAmy X. Zhang
2025
CHI

AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, but can be unhelpful or even annoying, due to not fitting the group's preferences or… 

CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation

Peter JansenOyvind TafjordMarissa RadenskyPeter Clark
2025
ACL (Findings)

Despite the surge of interest in autonomous scientific discovery (ASD) of software artifacts (e.g., improved ML algorithms), current ASD systems face two key limitations: (1) they largely explore… 

Paloma: A Benchmark for Evaluating Language Model Fit

Ian MagnussonAkshita BhagiaValentin HofmannJesse Dodge
2024
NeurIPS

Language models (LMs) commonly report perplexity on monolithic data held out from training. Implicitly or explicitly, this data is composed of domains$\unicode{x2013}$varying distributions of… 

ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models

Benjamin NewmanYoonjoo LeeAakanksha NaikKyle Lo
2024
EMNLP

When conducting literature reviews, scientists often create literature review tables—tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and… 

SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design

Carl N. EdwardsAakanksha NaikTushar KhotTom Hope
2024
COLM

Predicting synergistic drug combinations can help accelerate discovery of cancer treatments, particularly therapies personalized to a patient’s specific tumor via biopsied cells. In this paper, we… 

CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support

Chao-Chun HsuErin BransomJenna SparksAakanksha Naik
2024
ACL

Literature review requires researchers to synthesize a large amount of information and is increasingly challenging as the scientific literature expands. In this work, we investigate the potential of… 

Overview of the Context24 Shared Task on Contextualizing Scientific Claims

Joel ChanAakanksha NaikMatthew AkamatsuJenna Sparks
2024
ACL • SDP

To appropriately interpret and use scientific claims for sensemaking and decision-making, it is critical to contextualize them, not just with textual evidence that the claim was in fact asserted,…