arXiv Machine Learning
Jul 9
Reward Valuation in Vision Language Models: Causal Mechanisms Underlying Anhedonia
arXiv:2607. 06626v1 Announce Type: new Abstract: Recent Vision-Language Models capture increasingly complex aspects of human cognition.
Reward Valuation in Large Language Models: Causal Induction of Anhedonia
The study investigates whether large language models (LLMs) exhibit reward valuation mechanisms analogous to human anhedonia by applying clinical tests designed for major depressive disorder. Researchers identified reward‑anticipatory units in state‑of‑the‑art AI models, showed that perturbing these units predicts Nucleus Accumbens activity, and caused the models to choose low‑effort, low‑reward tasks—mirroring human anhedonia. The findings suggest that specific reward‑valuation circuits in AI can functionally resemble those in humans, providing a mechanistic bridge between computational and neurobiological models of motivation.
Related stories
arXiv Computation and Language
4d ago
Better Behavioral Prediction, More Faithful Model Ablations? Evidence from Sequential Choice
The paper investigates whether input ablations on predictive models can reliably reveal the importance of information for explaining human sequential choice behavior. Using two synthetic bandit tasks with known generating policies, the authors compare GRUs, Transformers, a fine‑tuned LLaMA, and cognitive models under varied reward contributions. They find that while neural models can predict choices well, their responses to ablations often diverge from the true generating process, indicating that predictive accuracy alone does not guarantee faithful model ablations.
arXiv AI
Jul 10
A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents
arXiv:2607. 07753v1 Announce Type: cross Abstract: Modelling psychological disorders in artificial agents offers both a testbed for computational psychiatry and a lens on the failure modes of affective control.
arXiv Machine Learning
Aug 6
Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning
arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.
arXiv AI
Jul 7
The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.
arXiv AI
Jun 16
Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
arXiv:2606. 15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it.
arXiv AI
Jul 7
Attention Limited Reward Learning
arXiv:2607. 04590v1 Announce Type: new Abstract: Pairwise human comparisons are a primary interface through which modern AI systems learn human preferences.
arXiv Machine Learning
Sep 24
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
arXiv:2609.27532v1 Announce Type: new Abstract: Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The...
arXiv AI
4d ago
Signatures of semantic search in the activations of large language models
arXiv:2609.35599v2 Announce Type: replace Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...
arXiv AI
Aug 6
Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning
arXiv:2608. 04663v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning often adds social terms to individual rewards, yet the scale of those terms is usually chosen by hand.
arXiv AI
Jul 22
Measuring Reward-Seeking via Contrastive Belief Updates
arXiv:2607. 18966v1 Announce Type: new Abstract: Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective.
arXiv Machine Learning
Sep 2
Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training
arXiv:2609.01170v1 Announce Type: new Abstract: Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organizati...