Uncertainty quantification (UQ) methods for large language models are predominantly designed by hand based on domain knowledge and heuristics, limiting their scalability and generality. We apply LLM-powered evolutionary search to automatically discover unsupervised UQ methods represented as Python programs. On the task of atomic claim verification, our evolved methods outperform strong manually-designed baselines, achieving up to 6.7% relative ROC-AUC improvement across 9 datasets while generalizing robustly out-of-distribution. Qualitative analysis reveals that different LLMs employ qualitatively distinct evolutionary strategies: Claude models consistently design high-feature-count linear estimators, while Gpt-oss-120B gravitates toward simpler and more interpretable positional weighting schemes. Surprisingly, only Sonnet 4.5 and Opus 4.5 reliably leverage increased method complexity to improve performance -- Opus 4.6 shows an unexpected regression relative to its predecessor. Overall, our results indicate that LLM-powered evolutionary search is a promising paradigm for automated, interpretable hallucination detector design.
Light over Heavy: Automated Performance Requirements Quantification with Linguistic Inducement
School of Computer Science and Engineering University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);IDEAS Lab, School of Computer Science University of Birmingham(伯明翰大学计算机科学学院)
A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees
The Institute of Intelligent Computing, University of Electronic Science and Technology of China(电子科技大学智能计算学院);College of Systems Engineering, National University of Defense Technology(国防科技大学系统工程学院);Academy of Military Medical Sciences(军事医学科学院)
Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection
International Centre for Theoretical Physics Asia-Pacific(国际理论物理中心亚太中心);University of Chinese Academy of Sciences(中国科学院大学);Taiji Laboratory for Gravitational Wave Universe(引力波宇宙Taiji实验室);Tsinghua University(清华大学)
REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming
King Fahd University of Petroleum & Minerals(法赫德国王石油与矿产大学);Imam Abdulrahman Bin Faisal University(伊玛目阿卜杜勒拉赫曼·本·费萨尔大学);SDAIA-KFUPM Joint Research Center for Artificial Intelligence(SDAIA-KFUPM人工智能联合研究中心)
Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电气与计算机工程系);Department of Computer Science, Universidad de Jaén(西班牙Jaén大学计算机科学系);School of Computer and Mathematical Sciences, University of Adelaide(阿德莱德大学计算机与数学科学学院);Leiden Institute of Advanced Computer Science, University Leiden(莱顿大学先进计算机科学研究所);Department of Mathematics and Computing, Dr. B. R. Ambedkar National Institute of Technology(德拉·B·R·阿姆贝卡尔国立理工学院数学与计算系)
Divided by discipline? A systematic literature review on the quantification of online sexism and misogyny using a semi-automated approach
University of Exeter(埃克塞特大学);Oxford Internet Institute, University of Oxford(牛津互联网研究所,牛津大学);Ewha Womans University(成均馆大学);Alan Turing Institute(艾伦·图灵研究所)