Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering
The article discusses a novel approach for enhancing Visual Question Answering (VQA) by distilling rules from Large Language Models (LLMs). This method allows for the adaptation of logic-based representations in response to changing task requirements, improving interpretability. The authors demonstrate that their approach is effective across various VQA datasets with minimal examples needed for accurate rule generation.
- ▪Visual Question Answering (VQA) requires integrating multimodal input and reasoning.
- ▪The proposed method prompts an LLM to extend initial VQA reasoning theories expressed as answer-set programs.
- ▪The approach has shown effectiveness across diverse VQA datasets, requiring only a few examples to generate correct rules.
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/2606.03269 |
| Publication time | Wed, 03 Jun 2026 00:00:00 -0400 |
| Retrieval time | 2026-06-03T04:11:55.408Z |
| Last seen | 2026-06-03T04:11:55.408Z |
| 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 | 9uWf3eflEQlS |
| 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:2606.03269 (cs) [Submitted on 2 Jun 2026] Title:Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering Authors:Thomas Eiter, Nelson Higuera Ruiz, Johannes Oetsch View a PDF of the paper titled Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering, by Thomas Eiter and 2 other authors View PDF Abstract:Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning. Modular approaches that incorporate logic-based representations into the reasoning component offer clear advantages over end-to-end trained systems, particularly in terms of interpretability.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
