We have 6 of 143 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Under injected silent failures, EVIGATE improves task success by 18.7 points in live ALFWorld agents, 5.0 in WebShop, and 5.1 in a phone simulator, and it also outperforms random vetoes at the same rate.
Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact decides whether an action is authorized, frontier open-weight agents do both, and one behavior marks the lie: retroactive permission laundering, acting and then asking pe...
A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each complete answer's probability to a power above one and renormalizes, shifting probabili...
Chopthin-Consensus Power Sampling (CCPS) is introduced, demonstrating that diversity-preserving resampling and diversity-aware selection are complementary mechanisms for training-free LLM reasoning.
Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challenge this assumption with FairGap, the first benchmark to jointly evaluate recommendation fairness at two levels: observable output shift (OB...
HYMELL is introduced, a hybrid three-level framework for estimating LLM inference latency and energy by combining analytical modeling with machine learning (ML), which enables fast, hardware-free design space exploration and energy-efficient optimization.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
