Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering operations such as fine-tuning (including PPO/DPO), pruning/compression, and model merging. We propose \textsc{AttnDiff}, a data-efficient white-box framework that extracts fingerprints from models via intrinsic information-routing behavior. \textsc{AttnDiff} probes minimally edited prompt pairs that induce controlled semantic conflicts, captures differential attention patterns, summarizes them with compact spectral descriptors, and compares models using CKA. Across Llama-2/3 and Qwen2.5 (3B--14B) and additional open-source families, it yields high similarity for related derivatives while separating unrelated model families (e.g., $>0.98$ vs.\ $<0.22$ with $M=60$ probes). With 5--60 multi-domain probes, it supports practical provenance verification and accountability.
Mengting Li, Xilong Cheng, Zhihao Xiao, Zhenhua Xu, Jingyuan Zhou, Linfeng Li, Long Zhang, Borui Cai 等 9 位作者
LLM-based role-playing agents are fluent at imitating a character's style, yet struggle to make role-consistent decisions over long narrative horizons. Such decisions are shaped by experiences spanning many prior scenes, which are often partial and may point in different directions. Existing methods inject cross-scene memories as context, but do not reason about how past events shape a character's current motivations and behavior. We propose MemRole, a framework that makes this memory-to-decision process explicit. It introduces Long-Horizon Memory Thinking (LHMT), a reasoning schema that decomposes hidden reasoning into context understanding, memory activation, and response strategy planning, trained on a novel-derived dataset whose character-grounded, timeline-constrained memory pools limit each character to what it could plausibly know at the current narrative point. Beyond supervised fine-tuning, we propose Self-Refining On-Policy Self-Distillation (SR-OPSD): the model critiques its own rollouts against the reference under a data-driven rubric, and a critique-conditioned teacher view of the same model distills token-level guidance back into the policy. MemRole-32B improves over its backbone by 15.2 points on memory-grounded role-playing, performs on par with frontier LLMs such as GPT-5.4, and achieves the best character-motivation recognition accuracy on CroSS-MR.