LAMP: Extracting Locally Linear Decision Surfaces from LLM World Models
원문 초록
We introduce LAMP (Linear Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how reliably a model maps its stated reasons to its predictions through a locally linear model approximating the decision surface. LAMP treats the model's own self-reported explanations as a coordinate system and fits a locally linear surrogate that links those weights to the model's output. By doing so, it reveals which stated factors steer the model's decisions, and by how much. We apply LAMP to three tasks: sentiment analysis, controversial-topic detection, and safety-prompt auditing. Across these tasks, LAMP reveals that many LLMs exhibit locally linear decision landscapes. In addition, these surfaces correlate with human judgments on explanation quality and, on a clinical case-file data set, aligns with expert assessments. Since LAMP operates without requiring access to model gradients, logits, or internal activations, it serves as a practical and lightweight framework for auditing proprietary language models, and enabling assessment of whether a model behaves consistently with the explanations it provides.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DCR: Quantifying Data Contamination in LLMs Evaluation
AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles
Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
CAtCh: Cognitive Assessment through Cookie Thief
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.