arxivJul 24bullish

DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations

arXiv:2606.08532v5 Announce Type: replace Abstract: Modern artificial intelligence excels at prediction but cannot explain. From large language models to AI-for-science systems, today's machines answer what by recombining patterns already present in the human literature, yet they cannot reason out w

TR1 model #explanation #scientific-discovery #hypothesis-generation Read on arxiv →

arxivJun 15

Multi-component Causal Tracing in Large Language Models

arXiv:2606.03085v2 Announce Type: replace-cross Abstract: Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computations to specific metrics of interest, quantifying the LLM's b

#machine-learning #research #language-models Read on arxiv →

arxivMay 26

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

arXiv:2605.25903v1 Announce Type: new Abstract: Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own activations. We introduce Universal Activation Verbalizer (UAV), a framewo

UN1 model #explanation #transfer-learning #natural-language Read on arxiv →

arxivMay 13bullish

LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs

arXiv:2605.09542v1 Announce Type: new Abstract: Extracting multi-step explanations from knowledge graphs poses a combinatorial challenge requiring both heuristic guidance (as candidates proliferate with depth) and credit assignment (as path quality emerges over extended sequences). Frontier LLMs, st

FRTE2 models #neuro-symbolic #knowledge-graphs #reasoning Read on arxiv →