5 papers
PRISM: Probability Reallocation with In-Span Masking for Knowledge-Sensitive Alignment
Chenning Xu, Mao Zheng, Mingyang Song
Supervised fine-tuning (SFT) with token-level hard labels can amplify overconfident imitation of factually unsupported targets, causing hallucinations that propagate in multi-sente…
Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge
Mingyang Song, Mao Zheng, Chenning Xu
The paradigm of LLM-as-a-judge relies on a critical assumption, namely that high inter-evaluator agreement indicates reliable and objective evaluation. We present two complementary…
PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation
Chenning Xu, Mao Zheng, Mingyu Zheng +1
Podcast script generation requires LLMs to synthesize structured, context-grounded dialogue from diverse inputs, yet systematic evaluation resources for this task remain limited. T…
LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
Fangxun Shu, Yue Liao, Le Zhuo +14
We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM…
SAG: Style-Aligned Article Generation via Model Collaboration
Chenning Xu, Fangxun Shu, Dian Jin +2
Large language models (LLMs) have increased the demand for personalized and stylish content generation. However, closed-source models like GPT-4 present limitations in optimization…