Existing text representations such as embeddings and bag-of-words are not suitable for rule learning due to their high dimensionality and absent or questionable feature-level interpretability. This article explores whether large language models (LLMs) could address this by extracting a small number of interpretable features from text. We demonstrate this process on two datasets (CORD-19 and M17+) containing several thousand scientific articles from multiple disciplines and a target being a proxy for research impact. An evaluation based on testing for the statistically significant correlation with research impact has shown that LLama 2-generated features are semantically meaningful. We consequently used these generated features in text classification to predict the binary target variable representing the citation rate for the CORD-19 dataset and the ordinal 5-class target representing an expert-awarded grade in the M17+ dataset. Machine-learning models trained on the LLM-generated features provided similar predictive performance to the state-of-the-art embedding model SciBERT for scientific text. The LLM used only 62 features compared to 768 features in SciBERT embeddings, and these features were directly interpretable, corresponding to notions such as article methodological rigor, novelty, or grammatical correctness. As the final step, we extract a small number of well-interpretable action rules. Consistently competitive results obtained with the same LLM feature set across both thematically diverse datasets show that this approach generalizes across domains.
Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders
The University of Sheffield(谢菲尔德大学);Tianjin University(天津大学);University of Manchester(曼彻斯特大学);Kyushu University(九州大学);City University of Hong Kong(香港城市大学)
ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);School of Electronics Engineering and Computer Science, Peking University(北京大学电子工程与计算机科学学院)
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Nanjing University of Aeronautics and Astronautics(南京航空航天大学);The 63rd Research Institute, National University of Defense Technology, Nanjing(国防科技大学第六三研究所,南京)
IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
Computer Science and Engineering, Hong Kong University of Science and Technology(香港科技大学计算机科学与工程学院);School of Computing and Data Science, The University of Hong Kong(香港大学计算机科学与数据科学学院);School of Information Science & Engineering, Lanzhou University(兰州大学信息科学与工程学院);Max Planck Institute for Security and Privacy(安全与隐私研究所);Computer Science, The University of Michigan(密歇根大学计算机科学系);Center for Data Science, Peking University(北京大学数据科学中心)
Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading
Department of Physics, University of Cambridge, Cambridge, UK(剑桥大学物理系);Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK(剑桥大学应用数学与理论物理系)
Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scores
Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data
University of Pennsylvania(宾夕法尼亚大学);Stony Brook University(石溪大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Medical University of South Carolina(南卡罗来纳医科大学);Cedars-Sinai Medical Center(西格拉姆山医疗中心)
MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
The University of Texas at Arlington(德克萨斯大学阿灵顿分校);Sichuan University(四川大学);Northwestern University(西北大学);Indiana University(印第安纳大学);Emory University(埃默里大学);Nankai University(南开大学);MountainLion Research(MountainLion研究机构);Xi’an University of Electronic Science and Technology(西安电子科技大学);Kyoto University(京都大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Nanjing university(南京大学);Tsinghua University(清华大学);University of Toronto(多伦多大学)
Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategies
Software Engineering Institute, AI Division, Carnegie Mellon University(卡内基梅隆大学软件工程院,人工智能分部);Department of Statistics & Data Science, Carnegie Mellon University(卡内基梅隆大学统计与数据科学系)