229 citations · 597 across the 19 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.CL2026
Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content Moderation
Danting Zhang, Bei Peng, Robert Loftin
Large language models (LLMs) demonstrate strong performance on standard content moderation benchmarks. However, these benchmarks often aggregate multiple moderation criteria into a…
cs.LG2026
Online Self-Weighted Fine-Tuning
Haiquan Wen, Yiwei He, Bei Peng +1
Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence over training queries. Rein…
cs.AI2026
LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
Manith Adikari, Bei Peng, Samuele Vinanzi +1
Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, c…