8 papers
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
Yijiang River Dong, Zexue He, Cheng Yu +9
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce resp…
From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement
Leijun Zhou, Yanke Yu, Zhihao Liu +10
Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued development. Recent methods allow language agents to retain changes to their p…
Multi-agent AI systems outperform human teams in creativity
Tiancheng Hu, Yixuan Jiang, Haotian Li +5
Although artificial intelligence (AI) now matches or exceeds human performance across numerous cognitive tasks, creativity remains a highly contested frontier. As AI systems based…
Value of Information: A Framework for Human-Agent Communication
Yijiang River Dong, Tiancheng Hu, Zheng Hui +4
Large Language Model (LLM) agents deployed for real-world tasks face a fundamental dilemma: user requests are underspecified, yet agents must decide whether to act on incomplete in…
Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding
Yijiang River Dong, Tiancheng Hu, Zheng Hui +1
Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting in…
Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
Beiduo Chen, Tiancheng Hu, Caiqi Zhang +3
Reasoning-tuned LLMs utilizing long Chain-of-Thought (CoT) excel at single-answer tasks, yet their ability to model Human Label Variation--which requires capturing probabilistic am…
Confidence Estimation for LLMs in Multi-turn Interactions
Caiqi Zhang, Ruihan Yang, Xiaochen Zhu +5
While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings.…
Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models
Ej Zhou, Caiqi Zhang, Tiancheng Hu +4
Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large Language Models (LLMs). However, t…