The Value Axis: Language Models Encode Whether They're on the Right Track
We investigate whether language models internally track the value of their current trajectory, defined as the likelihood that their ongoing strategy will achieve their goals. Using synthetic, in-context reinforcement learning data, we construct a "value" axis for Qwen3-8B. We find that activations along this axis distinguish between high vs. low verbalized confidence, rollouts without and with backtracking, and correct vs. corrupted code. Steering towards high value causally suppresses self-correction and reduces explanatory verbosity, while steering towards low value induces backtracking and exploration. We demonstrate that direct preference optimization (DPO) can increase the internal value of rewarded behaviors (e.g. use a certain word), causing the model to act more confidently after exhibiting them. Finally, we apply the value axis to study in-the-wild settings. For example, we find that Qwen assigns low value to politically sensitive chat queries after post-training and that supervised fine-tuning increases internal confidence within the training domain. Our results suggest that language models linearly encode an estimate of expected goal success that modulates their confidence in pursuing a direction.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Geometric Scaling of Bayesian Inference in LLMs
Recent work has shown that small transformers trained in controlled "wind-tunnel'' settings can implement exact Bayesian inference, and that their training dynamics produce a geometric substrate -- low-dimensional value …
Bayesian InferenceAxis-Aligned Semantics for ODRL: Resolving Dimensional Ambiguity in Policy Constraints
The Open Digital Rights Language (ODRL) represents policy constraints as triples of a left operand, an operator, and a value. Several spatial operands, however, range over multi-axis domains such as width, height, and de…
The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
Large language models (LLMs) are routinely prompted to take on social roles ranging from individuals to institutions, yet it remains unclear whether their internal representations encode the granularity of such roles, fr…
A Unified Representation Underlying the Judgment of Large Language Models
A central architectural question for both biological and artificial intelligence is whether judgment relies on specialized modules or a unified, domain-general resource. While the discovery of decodable neural representa…
Probing Pre-Trained Language Models for Cross-Cultural Differences in Values
Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially harmful biases encoded in Pre-Trained Language models (PTLMs). However, there has been …