PRISM: Recovering Instruction Sets from Language Model Activations
As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior. This is difficult when models infer unintended subgoals, follow contextual cues, or are influenced by prompt injections and hidden objectives. While activation-to-language methods suggest that hidden states can reveal natural-language information, existing approaches are not designed to recover the full set of simultaneous instructions, constraints, prohibitions, and subgoals active in agentic settings. We formalize this problem as instruction set retrieval and introduce PRISM, an activation-conditioned interpreter that decodes hidden states from a frozen target model into a faithful bullet list of active instructions. Unlike prior activation-to-language methods, PRISM is trained to recover instruction sets directly, using judge-guided GRPO to reward covered instructions and penalize unsupported ones. Across benign, constrained, prompt-injection, and hidden-objective settings, PRISM outperforms activation-to-language baselines, especially on security-relevant objectives.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Visual instruction tuning refines pre-trained Multimodal Large Language Models (MLLMs) to enhance their real-world task performance. However, the rapid expansion of visual instruction datasets introduces significant data…
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. However, existing benchmarks largely rely on mixed…
Instruction FollowingLogical ReasoningPrism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning
Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-world deployment requires continuous adapta…
Language Through a Prism: A Spectral Approach for Multiscale Language Representations
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better ca…
Part-Of-Speech TaggingTopic ClassificationPRISM: Personalized Robotic Dataset Generation via Image-based Scene and Motion Synthesis
Recent advances in large-scale pretrained vision-language-action models have improved robot policy learning, but directly deploying such policies in user-specific environments remains challenging due to limited generaliz…
Motion Synthesis