Pith. sign in

REVIEW 6 cited by

Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities

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 2311.10227 v1 pith:Q56VHHRF submitted 2023-11-16 cs.AI cs.CL

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

Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others. Although ToM may come naturally to us, emulating it presents a challenge to even the most advanced Large Language Models (LLMs). Recent improvements to LLMs' reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought have seen limited applicability to ToM. In this paper, we turn to the prominent cognitive science theory "Simulation Theory" to bridge this gap. We introduce SimToM, a novel two-stage prompting framework inspired by Simulation Theory's notion of perspective-taking. To implement this idea on current ToM benchmarks, SimToM first filters context based on what the character in question knows before answering a question about their mental state. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods, and our analysis reveals the importance of perspective-taking to Theory-of-Mind capabilities. Our findings suggest perspective-taking as a promising direction for future research into improving LLMs' ToM capabilities.

Discussion (0). Continue with ORCID 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. PRISON: Unmasking the Criminal Potential of Large Language Models

    cs.CR 2025-06 conditional novelty 6.0 of 10

    PRISON gives a new roleplay-based benchmark showing current LLMs generate criminal-style traits at high rates but detect them poorly.

  2. Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes

    cs.CL 2025-06 conditional novelty 6.0 of 10

    LLMs show limited, task-dependent accuracy at choosing correct epistemic modals and attitude verbs in controlled stories, with better performance on necessity and fact statements than on possibility and belief statements.

  3. Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement

    cs.SE 2025-05 conditional novelty 6.0 of 10

    AlignMind, a multi-agent system with theory-of-mind helpers, refines software requirements through multi-round dialogue, outperforming a direct-prompt baseline in LLM-judged quality and lexical richness, at high token...

  4. Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies

    cs.CL 2025-07 reject novelty 4.0 of 10

    MoR fine-tunes Qwen2.5 on GPT-4o-selected reasoning templates, claiming up to 13.5% accuracy gains, but the reported gains are not robustly supported.

  5. UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs

    cs.CL 2025-06 reject novelty 4.0 of 10

    A new benchmark, UniToMBench, is proposed for evaluating Theory of Mind in LLMs, but its evaluation results are mixed and do not substantiate the claimed improvements.

  6. When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?

    cs.HC 2025-10 conditional novelty 3.0 of 10

    Researchers' claims of AI theory of mind are really about behavioral prediction, so AI evaluation should shift from isolated cognitive tests to human-AI interaction.

Pith tools