Skip to content

Better Behavioral Prediction, More Faithful Model Ablations? Evidence from Sequential Choice

Sep 2026 · arXiv.org · Vol abs/2609.36097 · 0 citations · 22 references
Computer Science Biology

TL;DR

Three findings emerge: in the restless task, neural models trained without rewards predict held-out choices better than four simple training-fitted behavioral baselines, and at some reward weights, neural networks predict better than a pooled reinforcement-learning model but have less faithful changes in choice probabilities.

Abstract

Using predictive models to explain cognition requires more than accurate behavioral predictions. Input ablations offer an appealing route: remove information from a model and interpret the resulting performance change as evidence of its importance for behavior. Yet this inference assumes that the model's dependence on information reflects the dependence of the process generating the behavior. We test it in two synthetic sequential bandit tasks with known generating policies, where past choices can remain informative when feedback is unavailable to a predictor. We compare GRUs and Transformers trained from scratch, a fine-tuned LLaMA model, and cognitive models across systematically varied reward contributions. Our analyses distinguish prediction after training without reward observations from the response of a fixed predictor to donor-reward replacement. Three findings emerge. First, in the restless task, neural models trained without rewards predict held-out choices better than four simple training-fitted behavioral baselines. Second, under matched donor replacement, accurate predictors can respond much less than the known generator. Third, at some reward weights, neural networks predict better than a pooled reinforcement-learning model but have less faithful changes in choice probabilities; the model ordering differs between the two tasks. These independent-test results separate information sufficient for prediction from response fidelity under a specified ablation in sequential choice. They motivate validating model-ablation responses independently of predictive performance before using them to infer how the observed behavior was generated.

View source

Similar papers

#machine learning Preprint Oct 2026

Task Inference Beyond Least Squares in Behavioral Foundation Models

Behavioral Foundation Models (BFMs) aim to solve a wide range of downstream tasks without test-time policy learning by inferring a task vector from the reward function. While efficient, the retrieved policies are often suboptimal because of how this task vector is inferred, typically with ordinary least squares (OLS)....

Kuan-Hsun Tu, Chi-Hsun Chiang, Hsin-Wei Chen et al. · 0 citations
#machine learning Preprint Aug 2026

More accurate behavioral predictions with hybrid Bayesian-connectionist models

BBT outperforms traditional approaches at predicting human behavior while also revealing psychological insights, resulting in models that can both mimic Bayesian priors and capture heuristics and biases that violate simple modeling assumptions.

Brenden M. Lake, A. Jagadish, Guang-Yuan Jiang · 0 citations
Conference Open access Sep 2026

Empirical Evidence and Analysis of a Critical Pitfall in Reward Learning from Human Feedback

This work provides the first comprehensive empirical investigation of humans' internal models play a mediating role in feedback behaviour through a randomized controlled trial and shows that this relationship is invariant across visual contexts and is robust to three common feedback types.

Taha Shaheen, S. West, Yu Zhang · 0 citations
#machine learning Preprint Oct 2026

When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models

The component that dominates a latent world model's prediction error need not be the one whose repair most improves action selection. We show this by comparing action sequences from identical physical starts and separating endpoint error into a candidate-pool center and action-relative responses. Across four model fami...

Rui Min, Xian-Yao Li, Fang Xu et al. · 1 citation

RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback

This work proposes RewardExplainer, a framework that obtains feedback from the target reward model through counterfactual rewriting and uses this feedback to further optimize the explainer, enabling the explainer to more faithfully capture the target RM's scoring preferences and sensitive behaviors than single-pass gen...

Jing-Yi He, Ni-Er Wu, Shuang Liu et al. · 0 citations

What Pretraining and Midtraining Make Learnable from Rewards?

A reward can identify a correct answer while leaving the computation needed for new inputs undetermined. We study how pretraining and midtraining supply the information and computation that make reward adaptation effective. In sequential state computation and contextual memory, we characterize mechanisms that agree on...

Chi-Wun Yang, Xiao-Yu Li · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.