4 papers
CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation
Bingzhe Wu, Haotian Lu, Yuchen Mou
Current large language models (LLMs), even those explicitly trained for reasoning, often struggle with ambiguous content moderation cases due to misleading "decision shortcuts" emb…
CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs
Haotian Lu, Yuchen Mou, Bingzhe Wu
Content moderation in online platforms faces persistent challenges due to the evolving complexity of user-generated content and the limitations of traditional rule-based and machin…
LiveProteinBench: A Contamination-Free Benchmark for Assessing Models' Specialized Capabilities in Protein Science
Dingyi Rong, Zijian Chen, Qi Jia +4
In contrast to their remarkable performance on general knowledge QA, the true abilities of Large Language Models (LLMs) in tasks demanding deep, specialized reasoning, such as in p…
EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization
Dingyi Rong, Haotian Lu, Wenzhuo Zheng +3
Designing protein sequences with optimal energetic stability is a key challenge in protein inverse folding, as current deep learning methods are primarily trained by maximizing seq…