SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909687951130624 |
|---|---|
| author | Zhao, Runcong Zhu, Qinglin Xu, Hainiu Liang, Bin Gui, Lin He, Yulan |
| author_facet | Zhao, Runcong Zhu, Qinglin Xu, Hainiu Liang, Bin Gui, Lin He, Yulan |
| contents | Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThought, a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. The system constructs editable character relationship graphs, refines them using seven types of logical constraints, and enables real-time validation and conflict resolution through an interactive interface. To support logical supervision and explainable social analysis, we release a dataset of 160 interpersonal relationships with corresponding logical structures. Experiments show that SymbolicThought improves annotation accuracy and consistency while significantly reducing time cost, offering a practical tool for narrative understanding, explainable AI, and LLM evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04189 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding Zhao, Runcong Zhu, Qinglin Xu, Hainiu Liang, Bin Gui, Lin He, Yulan Computation and Language Artificial Intelligence Human-Computer Interaction Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThought, a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. The system constructs editable character relationship graphs, refines them using seven types of logical constraints, and enables real-time validation and conflict resolution through an interactive interface. To support logical supervision and explainable social analysis, we release a dataset of 160 interpersonal relationships with corresponding logical structures. Experiments show that SymbolicThought improves annotation accuracy and consistency while significantly reducing time cost, offering a practical tool for narrative understanding, explainable AI, and LLM evaluation. |
| title | SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2507.04189 |