7 citations · 13 across the 16 of their papers we have counts for
7 papers · 1 filter
Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States
Difan Jiao, Ashton Anderson
Language model agents can now perform sophisticated sequences of actions via tools and harnesses, which has increased the scope of the damage they can cause. Guard models, however,…
Tandem Reinforcement Learning with Verifiable Rewards
Difan Jiao, Raghav Singhal, Robert West +1
Reinforcement learning with verifiable rewards (RLVR) has driven substantial gains in language-model reasoning. However, models fine-tuned with RLVR need not remain compatible with…
Chessformer: A Unified Architecture for Chess Modeling
Daniel Monroe, George Eilender, Philip Chalmers +2
Chess has long served as a canonical testbed for artificial intelligence, but modeling approaches for its central tasks have diverged. Maximizing playing strength, predicting human…
LLM Safety From Within: Detecting Harmful Content with Internal Representations
Difan Jiao, Yilun Liu, Ye Yuan +4
Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and o…
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Difan Jiao, Qianfeng Wen, Blair Yang +2
We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (G…
Grounded Chess Reasoning in Language Models via Master Distillation
Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert +4
Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introduce a general framework for dist…
Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
Amogh Inamdar, Zhenwei Tang, Ashton Anderson +1
Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strat…