# Reward Valuation in Large Language Models: Causal Induction of Anhedonia

arXiv: https://arxiv.org/abs/2607.06626 · HTML: https://mlsanity.com/paper/2607.06626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 84 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers](https://mlsanity.com/paper/2106.15772/) (2021)
- [Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)](https://mlsanity.com/paper/1905.11833/) (2019)
- [The neuroconnectionist research programme](https://mlsanity.com/paper/2209.03718/) (2022)
- [Instruction-tuning Aligns LLMs to the Human Brain](https://mlsanity.com/paper/2312.00575/) (2023)
- [The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units](https://mlsanity.com/paper/2411.02280/) (2024)
- [From Language to Cognition: How LLMs Outgrow the Human Language Network](https://mlsanity.com/paper/2503.01830/) (2025)
- [Human-like object concept representations emerge naturally in multimodal large language models](https://mlsanity.com/paper/2407.01067/) (2024)
- [Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memory](https://mlsanity.com/paper/2409.15084/) (2024)
- [Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream](https://mlsanity.com/paper/2411.05712/) (2024)
- [TopoLM: brain-like spatio-functional organization in a topographic language model](https://mlsanity.com/paper/2410.11516/) (2024)
- [Contour Integration Underlies Human-Like Vision](https://mlsanity.com/paper/2504.05253/) (2025)
- [Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI](https://mlsanity.com/paper/2505.22563/) (2025)
- [PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health](https://mlsanity.com/paper/2412.16882/) (2024)
- [Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories](https://mlsanity.com/paper/2507.01966/) (2025)
- [Inducing Dyslexia in Vision Language Models](https://mlsanity.com/paper/2509.24597/) (2025)

## Abstract (arXiv)

Recent frontier models mimic complex aspects of human cognition. Here we ask whether this alignment extends into reward valuation, which we assess in a mechanistic framework. Specifically, we use clinical tests that were developed to evaluate anhedonia in human subjects with major depressive disorders. Mechanistically, anhedonia is frequently associated with dysregulation in the Nucleus Accumbens (NAc) and the broader dopaminergic reward system. While neuroimaging has localized these deficits, establishing a causal link between NAc activity and specific behavioral symptoms remains a challenge. We use these ideas from neuroscience to functionally identify reward-anticipatory units in state-of-the-art AI models, and evaluate their causal involvement via targeted perturbations. We find that not only are such model units predictive of NAc brain recordings, their perturbation also induces behavioral effects mirroring human anhedonia: the model opts for low-effort, low-reward tasks in effort-based decision-making paradigms. Crucially, our results demonstrate that this represents a specific deficit in self-centered reward valuation and anticipation--rather than a loss of task capability, reward calculation, or effort avoidance. This induced vulnerability aligns with clinical measures of anhedonia and motivation in humans, such as DARS and MAP-SR, instruments that contain no reward-related vocabulary, ruling out a purely lexical account of the perturbation effect. Taken together, our results suggest reward valuation circuits in AI models that functionally mimic those in humans.