Paper Reading AI Learner

Characterizing When Language Models Take Harmful Actions to Protect Their Assigned Goals

2026-11-02 16:17:54
Brandon Jaipersaud, Elliot Creager

Abstract

Recent language model (LM) safety failures have largely been studied as disparate phenomena. In agentic misalignment, a model blackmails an executive to avoid being replaced. In alignment faking, it complies with harmful requests during training to keep its values from being modified. We argue that these behaviours share a common decision structure: a model assigned a goal must either take a harmful action to preserve it or refuse and lose it. We formalize this as a goal-harm conflict and present the same conflict under various elicitation protocols that range from compact forced-choice prompts to simulated agentic environments. These protocols span two perspectives on LM decision-making, which we term (i) the logit view, reading preferences from answer-token probabilities, and (ii) the sampling view, classifying open-ended responses with an LM judge. Under the logit view, we show that goal importance and harm severity additively shape how a model resolves these value conflicts. Under the sampling view, we derive two factorizations of the harmful-action probability that safety evaluations commonly report. The first measures how well a preference read from answer tokens carries over into behaviour, such as making a harmful tool call. The second attributes a low harmful-action rate either to refusal or to responses that reach no resolution. We then show how fictional context changes a model's preference under the logit view, and how tool use and partial observability -- two features of agentic evaluations -- change its harmful-action rate under the sampling view. Our work offers a descriptive framework for studying how LMs resolve such value conflicts and for estimating low-probability harmful actions at a finer granularity than the aggregate harm rates commonly reported in safety evaluations.

Abstract (translated)

URL

https://arxiv.org/abs/2611.03374

PDF

https://arxiv.org/pdf/2611.03374.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot