6 papers
SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
Yue Huang, Xiangqi Wang, Xiangliang Zhang
In high-stakes scenarios-such as self-harm, legal, or medical queries-LLMs must be both trustworthy and helpful. However, these goals often conflict. We propose priority alignment,…
DyFlow: Dynamic Workflow Framework for Agentic Reasoning
Yanbo Wang, Zixiang Xu, Yue Huang +9
Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challe…
Causally-Enhanced Reinforcement Policy Optimization
Xiangqi Wang, Yue Huang, Yujun Zhou +3
Large language models (LLMs) trained with reinforcement objectives often achieve superficially correct answers via shortcut strategies, pairing correct outputs with spurious or unf…
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study
Yujun Zhou, Jiayi Ye, Zipeng Ling +8
Logical reasoning is a core capability for large language models (LLMs), yet existing benchmarks that rely solely on final-answer accuracy fail to capture the quality of the reason…
AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
Xiangqi Wang, Yue Huang, Yanbo Wang +4
LLMs often need effective configurations, like temperature and reasoning steps, to handle tasks requiring sophisticated reasoning and problem-solving, ranging from joke generation…
Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles
Yue Huang, Chujie Gao, Yujun Zhou +5
The Helpful, Honest, and Harmless (HHH) principle is a foundational framework for aligning AI systems with human values. However, existing interpretations of the HHH principle ofte…