Large Language Models (LLMs) often produce outputs that -- though plausible -- can lack consistency and reliability, particularly in ambiguous or complex scenarios. Challenges arise from ensuring that outputs align with both factual correctness and human intent. This is problematic in existing approaches that trade improved consistency for lower accuracy. To mitigate these challenges, we propose a novel game-theoretic approach to enhance consistency and reliability during the decoding stage of LLM output generation. Our method models the decoding process as a multistage Bayesian decoding game. This ensures consistency through Correctness Alignment and enhances reliability via Ambiguity Calibration. The model dynamically converges to a consensus on the most reliable outputs and distinguishes {Valid, Specious} outputs without human feedback or additional training. Our game design allows smaller models to outperform much larger models through game mechanisms (e.g., 78.1 LLaMA13B vs 76.6 PaLM540B), as well as integrating various LL strategies and models, demonstrating the potential of game-theoretic tools to improve the truthfulness and reliability of LLMs.
HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit
University of Technology Sydney(悉尼科技大学);City University of Macau(澳门城市大学);Meta;actAVA AI(actAVA人工智能公司);Microsoft AI(微软人工智能);Squirrel Ai Learning(松鼠人工智能学习公司);East China Normal University(华东师范大学)
Integrative Decoding: Improve Factuality via Implicit Self-consistency
The Hong Kong Polytechnic University(香港理工大学);Tsinghua University(清华大学);Microsoft Research(微软研究院);Microsoft Azure AI(微软Azure人工智能);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Hong Kong JC STEM Lab of Smart City(香港JC智能城市STEM实验室);City University of Hong Kong(香港城市大学);University of Sussex(苏塞克斯大学);Huazhong University of Science and Technology(华中科技大学);Fudan University(复旦大学);Lingnan University(岭大大学)
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所);Hong Kong University of Science and Technology(香港科技大学)
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
City University of Hong Kong(香港城市大学);National University of Singapore(新加坡国立大学);Shanghai Jiao Tong University(上海交通大学);Stanford University(斯坦福大学);Penn State University(宾夕法尼亚州立大学);Hong Kong University of Science and Technology(香港科技大学)
RAG-based EEG-to-Text Translation Using Deep Learning and LLMs
IAS-LAB, Department of Information Engineering, University of Padova(帕多瓦大学信息工程系IAS实验室);Padova Neuroscience Center(帕多瓦神经科学中心);Department of Health Technology, Technical University of Denmark(丹麦技术大学健康技术系)
DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning
Shanghai Jiao Tong University(上海交通大学);SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University(上海交通大学巴黎卓越工程师学院);The Chinese University of Hong Kong(香港中文大学)