Pith sign in

REVIEW 5 cited by

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 2305.14763 v1 pith:XX3YFJ72 submitted 2023-05-24 cs.CL

Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models

classification cs.CL
keywords llmsn-tomabilitiesexamplesmodelsanecdotalconclusionsexhibit
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The escalating debate on AI's capabilities warrants developing reliable metrics to assess machine "intelligence". Recently, many anecdotal examples were used to suggest that newer large language models (LLMs) like ChatGPT and GPT-4 exhibit Neural Theory-of-Mind (N-ToM); however, prior work reached conflicting conclusions regarding those abilities. We investigate the extent of LLMs' N-ToM through an extensive evaluation on 6 tasks and find that while LLMs exhibit certain N-ToM abilities, this behavior is far from being robust. We further examine the factors impacting performance on N-ToM tasks and discover that LLMs struggle with adversarial examples, indicating reliance on shallow heuristics rather than robust ToM abilities. We caution against drawing conclusions from anecdotal examples, limited benchmark testing, and using human-designed psychological tests to evaluate models.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Don't Make the LLM Read the Graph: Make the Graph Think

    cs.AI 2026-04 conditional novelty 7.0

    Under a governance-capability gap where more capable AI carries greater authority exposure, improvements in AI capability can reduce optimal deployment in high-loss environments.

  2. LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

    cs.CL 2026-07 conditional novelty 6.0

    A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.

  3. OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind

    cs.AI 2026-05 unverdicted novelty 5.0

    OSCToM uses RL-guided generation with an extended DSL and surrogate models to create nested belief conflict tasks, raising FANToM accuracy from 0.2% to 76% while being 6x more efficient.

  4. Don't Make the LLM Read the Graph: Make the Graph Think

    cs.AI 2026-04 unverdicted novelty 5.0

    Belief graphs improve LLM 2nd-order theory-of-mind performance in Hanabi when they gate action selection (100% vs 20%) but are mostly decorative as prompt context for strong models, with model-family-specific planner ...

  5. The Rise and Potential of Large Language Model Based Agents: A Survey

    cs.AI 2023-09 accept novelty 4.0

    The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.