← 研踪 PaperTrailarXiv:2608.02879 · v2
Sentence-Level Attribution for Black-Box Large Language Model Outputs via Energy-Based Surrogates
首次提交 2026-08-04 05:01
版本更新 2026-11-08 03:28
雷达观测 2026-11-10 11:14
摘要
The widespread adoption of proprietary Large Language Models (LLMs) via closed APIs poses an interpretability challenge. While white-box and gray-box (logit-dependent) attribution methods require internal model access, post-hoc attribution under a strictly black-box, text-only generative regime remains largely unexplored. To address this, we propose a model-agnostic, post-hoc attribution interpreter operating at the sentence level. We first train a transformer-based Energy-Based Model (EBM) as a surrogate to score the consistency between prompt and response sentences based on observed LLM generations. To prevent energy collapse and avoid a focus on superficial artifacts, we design contrastive negative samplers that evaluate partial counterfactual dependencies across prompt and response segments. This learned energy landscape then guides the training of a lightweight interpreter network. After model-specific training, the interpreter operates as a standalone tool; it estimates the influence of prompt sentences on a user-specified output sentence without requiring runtime API queries to the target LLM. Comprehensive experiments demonstrate that our EBM surrogate captures nuanced generative dependencies beyond surface-level heuristics, while the interpreter achieves competitive attribution quality with parameter-efficient, inference.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-08 03:28 · 最新观测版本
Sentence-Level Attribution for Black-Box Large Language Model Outputs via Energy-Based Surrogates
The widespread adoption of proprietary Large Language Models (LLMs) via closed APIs poses an interpretability challenge. While white-box and gray-box (logit-dependent) attribution methods require internal model access, post-hoc attribution under a strictly black-box, text-only generative regime remains largely unexplored. To address this, we propose a model-agnostic, post-hoc attribution interpreter operating at the sentence level. We first train a transformer-based Energy-Based Model (EBM) as a surrogate to score the consistency between prompt and response sentences based on observed LLM generations. To prevent energy collapse and avoid a focus on superficial artifacts, we design contrastive negative samplers that evaluate partial counterfactual dependencies across prompt and response segments. This learned energy landscape then guides the training of a lightweight interpreter network. After model-specific training, the interpreter operates as a standalone tool; it estimates the influence of prompt sentences on a user-specified output sentence without requiring runtime API queries to the target LLM. Comprehensive experiments demonstrate that our EBM surrogate captures nuanced generative dependencies beyond surface-level heuristics, while the interpreter achieves competitive attribution quality with parameter-efficient, inference.
查看此版本解读 →查看此版本原文 ↗