Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026 · 8 citations)
Generative reward models (GRMs) judge LLM outputs using chain-of-thought (CoT) reasoning. They have two weaknesses. They spend reasoning effort on every input, including easy ones. They also pick among sampled reasoning chains by voting, which cannot separate sound chains from ones that only look convincing. The…
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026 · 6 citations)
Supervised fine-tuning (SFT) is usually treated as a reliable way to specialize LLMs. The authors show, however, that converged models still get part of their own training set wrong. They call this the Incomplete Learning Phenomenon (ILP), distinguish it from catastrophic forgetting and machine unlearning, and…
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories (2026 · 1 citation)
Search-based data generation with Monte Carlo Tree Search (MCTS) usually keeps only the best-scoring solution path and throws away the rest.

Co-authors here

12 of 13 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 15 times (of the 149,439 papers whose bibliographies we read); 6 citing papers with a page here →.

Updated 31 October 2026