paper-with-me

홈 › Papers

Overcoming Knowledge Discrepancies: Structuring Reasoning Threads through Knowledge Balancing in Interactive Scenarios

2025-08-16 · Daniel Burkhardt, Xiangwei Cheng arxiv

Reasoning in interactive problem solving scenarios requires models to construct reasoning threads that reflect user understanding and align with structured domain knowledge. However, current reasoning models often lack explicit semantic hierarchies, user-domain knowledge alignment, and principled mechanisms to prune reasoning threads for effectiveness. These limitations result in lengthy generic output that does not guide users through goal-oriented reasoning steps. To address this, we propose a prototype-inspired, two-phases Reasoning-Threads-Evaluation (ReT-Eval) framework, drawing inspiration from human-like reasoning strategies that emphasize structured knowledge reuse. In the first phase, semantically relevant knowledge structures are extracted from a sparse domain knowledge graph using a graph neural network and enriched with intrinsic large language model knowledge to resolve knowledge discrepancies. In the second phase, these threads are evaluated and pruned using a reward-guided strategy aimed at maintaining semantic coherence to generate effective reasoning threads. Experiments and expert evaluations show that ReT-Eval enhances user understanding and outperforms state-of-the-art reasoning models.

📄 PDF Abstract BibTeX arXiv:2508.12100

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural Network

Similar Papers 제목 키워드 기반

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation

2025-02-16 · Pengcheng Jiang, Lang Cao, Ruike Zhu, Minhao Jiang 외

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augme…

graph constructionKnowledge GraphsLanguage ModelingLanguage Modelling+3

Temporal reasoning for timeline summarisation in social media

2024-12-30 · Jiayu Song, Mahmud Akhter, Dana Atzil Slonim, Maria Liakata

This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarization, the task of summarising long texts containing sequences of events, …

Knowledge DistillationTimeline Summarization

Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning

2025-07-22 · Hongyin Luo, Nathaniel Morgan, Tina Li, Derek Zhao 외 arxiv

To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional probl…

Information Retrieval

A Survey on Retrieval And Structuring Augmented Generation with Large Language Models

2025-09-12 · Pengcheng Jiang, Siru Ouyang, Yizhu Jiao, Ming Zhong 외 arxiv

Large Language Models (LLMs) have revolutionized natural language processing with their remarkable capabilities in text generation and reasoning. However, these models face critical challenges when deployed in real-world…

Information ExtractionInformation RetrievalText Generation

Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning

2024-05-17 · Jinchuan Zhang, Bei Hui, Chong Mu, Ming Sun 외

Temporal Knowledge Graph (TKG) reasoning focuses on predicting events through historical information within snapshots distributed on a timeline. Existing studies mainly concentrate on two perspectives of leveraging the h…