7 papers
OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets
Rheeya Uppaal, Seungwoo Lyu, Selina Sung +1
Safe completion requires models to provide useful assistance without enabling harm, but this behavior is difficult to evaluate with isolated prompts. We introduce OpenSafeIntent, a…
Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
Tianyang Han, Hengyu Shi, Junjie Hu +3
Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal wh…
SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent
Yikai Zhang, Jiaxin Pei, Kenan Li +9
Large language model agents have made strong progress on software engineering, yet current systems suffer from a context coupling problem: the standard code editing interface confl…
LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation
Dong Xu, Jialun Cao, Guozhao Mo +9
Formal specification is essential for rigorous program verification, yet writing correct specifications remains costly and difficult to automate. Although large language models (LL…
HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces
Ishita Kakkar, Enze Zhang, Rheeya Uppaal +1
Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. W…
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
Rheeya Uppaal, Apratim Dey, Yiting He +2
Recent alignment algorithms such as direct preference optimization (DPO) have been developed to improve the safety of large language models (LLMs) by training these models to match…