Small Foundation Models of Human Cognition and Behaviour

• URL: http://arxiv.org/abs/2608.05224v3
• Date: Tue, 11 Aug 2026 12:47:37 GMT
• Title: Small Foundation Models of Human Cognition and Behaviour
• Abstract summary: We train 14 models from 135M to 14B parameters across four architecture families on Psych-101.<n>Psych-101 is a dataset of 10.7 million trial-level choices from 160 experiments.<n>We show that small cognitively fine-tuned models show promise as noise ceiling estimators for psychological experiments.
• Score: 45.88028371034407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions. We train fourteen models from 135M to 14B parameters across four architecture families on Psych-101, a dataset of 10.7 million trial-level choices from 160 experiments. For in-distribution simulations, scale barely matters. The models fall within a narrow band, as though against a ceiling, and 0.6B to 1B parameters suffice to match a 70B baseline on held-out participants. Out-of-distribution, that band opens into a markedly steeper scaling gradient, with larger models clearly advantaged in generalisation to novel task structure. To determine what information these models use, we run two diagnostics. We progressively strip four prompt channels -- task instructions, experimental stimuli, outcome feedback, and choice history -- across 27 experiments, and permute trial order. Masking the content of stimuli and feedback destroys 75.7% of learned information and pushes models below chance, demonstrating that choice history alone does not account for performance. Permutation reveals invariance on tasks with independent trials but sensitivity where trial order is determined by prior responses. Small cognitively fine-tuned models therefore show promise as noise ceiling estimators for psychological experiments, though their scope remains bounded by the paradigms seen in training.

Related papers

• PhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us [0.7084863262134483]
  We present PhenoBench, an executable benchmark built around the Human Phenotype Project.<n>The benchmark defines 90 clinically grounded tasks across 15 domains and 26 input modalities.<n> Measurements showed question- and representation-dependent predictive value, including positive, near-zero, and negative changes in held-out performance.
  arXiv  Detail & Related papers  (2026-09-05T13:15:40Z)
• AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models [0.0]
  We introduce AgentWeave, a deterministic pre-inference routing layer that constructs a bounded model-visible action space.<n>Relative to all-tools exposure, AgentWeave presents 70.18% fewer tools, uses 61.70% fewer input tokens, and exhibits 50.95% lower mean local-model latency.
  arXiv  Detail & Related papers  (2026-08-24T10:38:08Z)
• Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search [50.16356451328644]
  Proving Shannon-type entropy inequalities is a fundamental task in information theory.<n>We investigate whether small-scale large language models, fine-tuned on atomic proof steps, can automate this process.<n>We show that GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples.
  arXiv  Detail & Related papers  (2026-06-04T05:43:12Z)
• Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation [4.702729080310267]
  We build a dataset of 11,488 idea pairs grounded in objective outcomes from PapersWithCode.<n>We train models to discover latent reasoning paths, achieving 71.35% acc. with interpretable justifications.<n>Our results demonstrate that compute-efficient small language models can serve as effective, objective verifiers.
  arXiv  Detail & Related papers  (2026-04-06T19:03:11Z)
• The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning [9.898274894485107]
  Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint.<n>We study this through a diagnose-measure-bridge-treat framework.
  arXiv  Detail & Related papers  (2026-03-30T21:36:09Z)
• Silhouette-based Gait Foundation Model [56.27974816297294]
  Building a unified gait foundation model requires addressing two longstanding barriers: Scalability and Generalization.<n>We introduce FoundationGait, the first scalable, self-supervised pretraining framework for gait understanding.
  arXiv  Detail & Related papers  (2025-11-30T01:53:41Z)
• Finetuning LLMs for Human Behavior Prediction in Social Science Experiments [9.470846958372974]
  Finetuning large language models (LLMs) directly on individual-level responses from past experiments meaningfully improves their accuracy.<n>We construct SocSci210 via an automatic pipeline, a dataset comprising 2.9 million responses from 400,491 participants in 210 social science experiments.<n>Our strongest model, Socrates-Qwen-14B, produces predictions that are 26% more aligned with distributions of human responses to diverse outcome questions.
  arXiv  Detail & Related papers  (2025-09-06T20:52:08Z)
• Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs [51.00909549291524]
  Large language models (LLMs) exhibit cognitive biases.<n>These biases vary across models and can be amplified by instruction tuning.<n>It remains unclear if these differences in biases stem from pretraining, finetuning, or even random noise.
  arXiv  Detail & Related papers  (2025-07-09T18:01:14Z)
• DataDecide: How to Predict Best Pretraining Data with Small Experiments [67.95896457895404]
  We release models, data, and evaluations in DataDecide -- the most extensive open suite of models over differences in data and scale.<n>We conduct controlled pretraining experiments across 25 corpora with differing sources, deduplication, and filtering up to 100B tokens, model sizes up to 1B parameters, and 3 random seeds.
  arXiv  Detail & Related papers  (2025-04-15T17:02:15Z)
• Dialectical Behavior Therapy Approach to LLM Prompting [1.433758865948252]
  Large language models demonstrated state-of-the-art results on various reasoning tasks when applying the chain-of-thought (CoT) prompting technique. We propose a novel prompting strategy inspired by Dialectical Behavioral Therapy (DBT) We show that prompts crafted with techniques significantly improve results on smaller models.
  arXiv  Detail & Related papers  (2024-10-10T09:58:03Z)
• A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics [4.220363193932374]
  We propose an efficient cosine similarity-based classification difficulty measure S. It is calculated from the number of classes and intra- and inter-class similarity metrics of the dataset. We show how a practitioner can use this measure to help select an efficient model 6 to 29x faster than through repeated training and testing.
  arXiv  Detail & Related papers  (2024-04-09T03:27:09Z)
• A Twin Neural Model for Uplift [59.38563723706796]
  Uplift is a particular case of conditional treatment effect modeling. We propose a new loss function defined by leveraging a connection with the Bayesian interpretation of the relative risk. We show our proposed method is competitive with the state-of-the-art in simulation setting and on real data from large scale randomized experiments.
  arXiv  Detail & Related papers  (2021-05-11T16:02:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.