5 papers
STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
Chenjun Xu, Zhennan Zhou, Zhan Su +3
Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking: models often generate low-yield reasoning that increases i…
MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining
Bingbing Wen, Sirajul Salekin, Feiyang Kang +4
Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimo…
Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
Chenjun Xu, Bingbing Wen, Bin Han +3
Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks. We…
Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
Yiwei Yang, Chung Peng Lee, Shangbin Feng +5
Finetuning can cause spurious correlations to arise between non-essential features and the target labels, but benchmarks to study these effects involve contrived settings and narro…
Know Your Limits: A Survey of Abstention in Large Language Models
Bingbing Wen, Jihan Yao, Shangbin Feng +4
Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM syst…