mlsanityData to 14 Oct 2026

SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding

arXiv 2507.04189 ↗First posted 5 Jul 2025cs.CL cs.AI cs.HCcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 7 of its 15 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

7 of 15 references.

References · 7

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  4. 2024The Faiss librarycited by 376
  5. 2024Secrets of RLHF in Large Language Models Part II: Reward Modelingcited by 171
  6. 2023The Generative AI Paradox: "What It Can Create, It May Not Understand"cited by 98
  7. 2024Large Language Models Fall Short: Understanding Complex Relationships in Detective Narrativescited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives
  2. 2022Understanding Narratives through Dimensions of Analogy
  3. 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
  4. 2025SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations
  5. 2023ARN: Analogical Reasoning on Narratives
  6. 2026PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models
  7. 2026From Symbolic to Natural-Language Relations: Rethinking Knowledge Graph Construction in the Era of Large Language Models
  8. 2024Extracting and Following Paths for Robust Relational Reasoning with Large Language Models