6 citations · 8 across the 7 of their papers we have counts for
8 papers
IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
Ziyu Chen, Yilun Zhao, Jiashuo Sun +3
Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this…
IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications
Yiling Ma, Yilun Zhao, Sihong Wu +2
A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation. We study the codifica…
ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
Yiling Ma, Yilun Zhao, Sihong Wu +3
As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revis…
Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning
Snigdha Paul, Manasi Patwardhan, Arman Cohan
Language models (LMs) are trained on static scientific corpora, whereas scientific knowledge continuously evolves through correction and revision. Scientific claims encoded within…
ResearchGym: Evaluating Language Model Agents on Real-World AI Research
Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan
We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers fr…
TESS 2: A Large-Scale Generalist Diffusion Language Model
Jaesung Tae, Hamish Ivison, Sachin Kumar +1
We introduce TESS 2, a general instruction-following diffusion language model that outperforms contemporary instruction-tuned diffusion models, as well as matches and sometimes exc…
NExT: Teaching Large Language Models to Reason about Code Execution
Ansong Ni, Miltiadis Allamanis, Arman Cohan +4
A fundamental skill among human developers is the ability to understand and reason about program execution. As an example, a programmer can mentally simulate code execution in natu…
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models
Martin Riddell, Ansong Ni, Arman Cohan
While large language models have achieved remarkable performance on various code generation benchmarks, there have been growing concerns regarding potential contamination of these…