Pith. sign in

REVIEW 6 cited by

LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.02784 v1 pith:M22GNPWP submitted 2024-08-05 cs.CL

classification cs.CL
keywords economicllmsbiasesbehaviorapproachbehavioralutilitycurrent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Humans are not homo economicus (i.e., rational economic beings). As humans, we exhibit systematic behavioral biases such as loss aversion, anchoring, framing, etc., which lead us to make suboptimal economic decisions. Insofar as such biases may be embedded in text data on which large language models (LLMs) are trained, to what extent are LLMs prone to the same behavioral biases? Understanding these biases in LLMs is crucial for deploying LLMs to support human decision-making. We propose utility theory-a paradigm at the core of modern economic theory-as an approach to evaluate the economic biases of LLMs. Utility theory enables the quantification and comparison of economic behavior against benchmarks such as perfect rationality or human behavior. To demonstrate our approach, we quantify and compare the economic behavior of a variety of open- and closed-source LLMs. We find that the economic behavior of current LLMs is neither entirely human-like nor entirely economicus-like. We also find that most current LLMs struggle to maintain consistent economic behavior across settings. Finally, we illustrate how our approach can measure the effect of interventions such as prompting on economic biases.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AI Financial Advice: Supply, Demand, and Life Cycle Implications

    econ.GN 2026-08 conditional novelty 8.0 of 10

    Following GPT-5.2 advice in a life cycle simulation would push most households toward higher equity participation, age-declining equity shares, and larger savings buffers, but advice inherits demand-side heterogeneity...

  2. Will Scaling Improve Social Simulation with LLMs?

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Using 85 controlled and 35 public LLMs, the authors show social-simulation accuracy generally improves with compute, but some behavioral and low-resource tasks do not scale.

  3. Out-of-Distribution Generalization of Risk Aversion in Language Models

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Risk aversion trained on ≤$100 gambles partially generalizes across 98 orders of magnitude in LMs, raising astronomical-stakes Cooperate rates from ~2% to ~39–70% depending on method.

  4. Temporal Preference Concepts and their Functions in a Large Language Model

    cs.LG 2026-05 unverdicted novelty 6.5 of 10

    Temporal preference in Qwen3-4B-Instruct-2507 localizes to layers 17–35 (especially L24 attention), has curved residual-stream geometry, is behaviorally unstable, and can be bidirectionally steered.

  5. CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs

    cs.AI 2025-08 reject novelty 6.0 of 10

    CHBench fits Level-K and Poisson cognitive hierarchy models to LLM game play and uses the fitted reasoning level as a benchmark score.

  6. The Effect of State Representation on LLM Agent Behavior in Dynamic Routing Games

    cs.AI 2025-06 conditional novelty 6.0 of 10

    In a repeated Braess routing game, LLM agents given summarized, regret-based, and own-action-only state representations converge closer to Nash equilibrium and behave more stably than agents given full chat transcript...

Pith tools