OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
The paper introduces OmniToM, a benchmark designed to evaluate the Theory of Mind capabilities in large language models (LLMs) through explicit belief modeling. It highlights the limitations of current evaluation methods that focus solely on end-point question answering, which may not accurately reflect a model's reasoning abilities. By requiring models to explicitly model belief structures, OmniToM aims to provide a more comprehensive assessment of LLMs' understanding of social dynamics.
- ▪OmniToM evaluates the ability of LLMs to infer knowledge, intentions, and emotions of actors within narratives.
- ▪The benchmark consists of two stages: Belief Extraction and Belief Labeling, assessing how well models track beliefs.
- ▪Current LLMs face challenges in transforming narrative facts into actors' beliefs and shared mental states.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.26322 |
| Publication time | Wed, 27 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-27T04:07:56.398Z |
| Last seen | 2026-05-27T04:07:56.398Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | ZxtRloTUlMhi |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.26322 (cs) [Submitted on 25 May 2026] Title:OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling Authors:Adam Bawatneh, Sagar Sapkota, Amrit Singh Bedi, Santu Karmaker, Mubarak Shah View a PDF of the paper titled OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling, by Adam Bawatneh and 4 other authors View PDF HTML (experimental) Abstract:Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
