Self-GIVE: Associative Thinking from Limited Structured Knowledge for Enhanced Large Language Model Reasoning

• URL: http://arxiv.org/abs/2505.15062v2
• Date: Sat, 24 May 2025 02:01:51 GMT
• Title: Self-GIVE: Associative Thinking from Limited Structured Knowledge for Enhanced Large Language Model Reasoning
• Authors: Jiashu He, Jinxuan Fan, Bowen Jiang, Ignacio Houine, Dan Roth, Alejandro Ribeiro,
• Abstract summary: Graph Inspired Veracity Extrapolation (GIVE) addresses this by using a knowledge graph (KG) to extrapolate structured knowledge.<n>We propose Self-GIVE, a retrieve-RL framework that enhances Large Language Models with automatic associative thinking.<n>Self-GIVE enhances the scalable integration of structured retrieval and reasoning with associative thinking.
• Score: 103.20561312320294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When addressing complex questions that require new information, people often associate the question with existing knowledge to derive a sensible answer. For instance, when evaluating whether melatonin aids insomnia, one might associate "hormones helping mental disorders" with "melatonin being a hormone and insomnia a mental disorder" to complete the reasoning. Large Language Models (LLMs) also require such associative thinking, particularly in resolving scientific inquiries when retrieved knowledge is insufficient and does not directly answer the question. Graph Inspired Veracity Extrapolation (GIVE) addresses this by using a knowledge graph (KG) to extrapolate structured knowledge. However, it involves the construction and pruning of many hypothetical triplets, which limits efficiency and generalizability. We propose Self-GIVE, a retrieve-RL framework that enhances LLMs with automatic associative thinking through reinforcement learning. Self-GIVE extracts structured information and entity sets to assist the model in linking to the queried concepts. We address GIVE's key limitations: (1) extensive LLM calls and token overhead for knowledge extrapolation, (2) difficulty in deploying on smaller LLMs (3B or 7B) due to complex instructions, and (3) inaccurate knowledge from LLM pruning. Specifically, after fine-tuning using self-GIVE with a 135 node UMLS KG, it improves the performance of the Qwen2.5 3B and 7B models by up to $\textbf{28.5%$\rightarrow$71.4%}$ and $\textbf{78.6$\rightarrow$90.5%}$ in samples $\textbf{unseen}$ in challenging biomedical QA tasks. In particular, Self-GIVE allows the 7B model to match or outperform GPT3.5 turbo with GIVE, while cutting token usage by over 90\%. Self-GIVE enhances the scalable integration of structured retrieval and reasoning with associative thinking.

Related papers

• Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering [24.821273655754222]
  Ontology-Guided Reverse Thinking (ORT) is a novel framework that constructs reasoning paths from purposes back to conditions.<n>ORT operates in three key phases: (1) using LLM to extract purpose labels and condition labels, (2) constructing label reasoning paths based on the KG ontology, and (3) using the label reasoning paths to guide knowledge retrieval.<n> Experiments on the WebQSP and CWQ datasets show that ORT achieves state-of-the-art performance and significantly enhances the capability of LLMs for KGQA.
  arXiv  Detail & Related papers  (2025-02-17T06:53:15Z)
• Logic Augmented Generation [1.534667887016089]
  Large Language Models (LLMs) overcome those limitations making them suitable in open-ended tasks and unstructured environments.<n>We envision Logic Augmented Generation (LAG) that combines the benefits of the two worlds.<n>We exemplify LAG in two tasks of collective intelligence, i.e., medical diagnostics and climate projections.
  arXiv  Detail & Related papers  (2024-11-21T10:54:35Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks [30.572064185770298]
  We propose a novel knowledge distillation method for learning the complex reasoning abilities of Large Language Models (LLMs)<n>NesyCD distills the general capabilities and specialized knowledge in LLMs using different manners.<n>Our experiments show that NesyCD significantly boosts SLMs' complex reasoning performance on in-domain (BBH, GSM8K) and out-of-domain (AGIEval, ARC) datasets.
  arXiv  Detail & Related papers  (2024-09-20T04:17:13Z)
• Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs [72.89652710634051]
  Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. We introduce Tree-of-Traversals, a novel zero-shot reasoning algorithm that enables augmentation of black-box LLMs with one or more KGs.
  arXiv  Detail & Related papers  (2024-07-31T06:01:24Z)
• Crafting Interpretable Embeddings by Asking LLMs Questions [89.49960984640363]
  Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. We introduce question-answering embeddings (QA-Emb), embeddings where each feature represents an answer to a yes/no question asked to an LLM. We use QA-Emb to flexibly generate interpretable models for predicting fMRI voxel responses to language stimuli.
  arXiv  Detail & Related papers  (2024-05-26T22:30:29Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [29.447300472617826]
  Think-on-Graph (ToG) is a new approach for external knowledge graphs (KG) in large language models (LLMs) ToG iteratively executes beam search on KG, discovers the most promising reasoning paths, and returns the most likely reasoning results. ToG achieves overall SOTA in 6 out of 9 datasets where most previous SOTAs rely on additional training.
  arXiv  Detail & Related papers  (2023-07-15T03:31:38Z)
• Empowering Language Models with Knowledge Graph Reasoning for Question Answering [117.79170629640525]
  We propose knOwledge REasOning empowered Language Model (OREO-LM) OREO-LM consists of a novel Knowledge Interaction Layer that can be flexibly plugged into existing Transformer-based LMs. We show significant performance gain, achieving state-of-art results in the Closed-Book setting.
  arXiv  Detail & Related papers  (2022-11-15T18:26:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.