Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience

• URL: http://arxiv.org/abs/2506.00842v2
• Date: Thu, 24 Jul 2025 19:34:51 GMT
• Title: Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience
• Abstract summary: Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases.<n>We introduce Contrastive Retrieval-Augmented Generation on Experience (CoRE), a framework that builds experience memory representations.<n> Experiments show CoRE significantly improves performance, achieving average gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks.
• Score: 8.270615745804557
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure transfer mechanisms. Unlike humans who seamlessly apply learned patterns across data modalities, LLMs struggle to infer implicit relationships embedded in tabular formats, especially in the absence of explicit structural guidance. To bridge this cognitive gap, we introduce Contrastive Retrieval-Augmented Generation on Experience (CoRE), a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning (ICL) to simulate human-like knowledge transfer. Experiments on Text-to-SQL and TableQA show CoRE significantly improves performance, achieving average gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks. Our Monte Carlo Tree Search (MCTS)-generated Experience Memory expands training data 8-9x, enhancing diversity and domain coverage. This training-free and continual method propels LLMs toward structured knowledge expertise.

Related papers

• ExpWeaver: LLM Agents Learn from Experience via Latent RAG [31.285842755478896]
  We propose ExpWeaver, a framework that enables LLM agents to learn from experience via latent retrieval-augmented generation.<n>ExpWeaver encodes experiences using the LLM's own hidden states, retrieves relevant experiences directly in latent space at each decoding step.<n>We evaluate ExpWeaver on 13 diverse tasks spanning question answering, reasoning, coding, scientific prediction, and recommendation.
  arXiv  Detail & Related papers  (2026-05-31T06:11:07Z)
• LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs [73.27182315028021]
  LANPO is a framework that cleanly separates the roles of feedback: language guides exploration, while numerical rewards drive optimization.<n>Our work provides a robust method for integrating historical experiences into the LLM RL loop, creating more effective and data-efficient learning agents.
  arXiv  Detail & Related papers  (2025-10-18T15:51:19Z)
• Experience Scaling: Post-Deployment Evolution For Large Language Models [44.48142891798125]
  We propose experience scaling, a framework for continuous post-deployment evolution for large language models (LLMs)<n>We validate the framework in simulated real-world scenarios involving generalization to previously unseen but related tasks, repetitive queries, and over-saturated knowledge stores.<n>Results demonstrate that structured post-deployment learning can extend LLM capabilities beyond the limits of static human-generated data.
  arXiv  Detail & Related papers  (2025-09-23T08:04:58Z)
• OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases [38.58409057214189]
  textbftextscOneEval is a benchmark to assess the knowledge-intensive reasoning capabilities of Large Language Models (LLMs)<n>textscOneEval comprises 4,019 carefully curated instances and includes a challenging subset, textscOneEvaltextsubscriptHard, consisting of 1,285 particularly difficult cases.<n>We release the textscOneEval datasets, evaluation scripts, and baseline results publicly, accompanied by a leaderboard to facilitate ongoing advancements in structured knowledge reasoning.
  arXiv  Detail & Related papers  (2025-06-14T17:16:05Z)
• Growing Through Experience: Scaling Episodic Grounding in Language Models [67.27024505353384]
  Language models (LMs) require robust episodic grounding to excel at physical planning tasks.<n>Current episodic grounding approaches struggle with scalability and integration.<n>We propose a scalable weak-to-strong episodic learning framework that effectively transfers episodic behaviors from smaller to larger LMs.
  arXiv  Detail & Related papers  (2025-06-02T04:52:19Z)
• LLM Inference Enhanced by External Knowledge: A Survey [16.319049759753106]
  This study explores strategies for using external knowledge to enhance large language models (LLMs)<n>Our comparative analysis highlights the trade-offs among interpretability, scalability, and performance.
  arXiv  Detail & Related papers  (2025-05-30T09:08:51Z)
• An Empirical Study of Federated Prompt Learning for Vision Language Model [50.73746120012352]
  This paper systematically investigates behavioral differences between language prompt learning and vision prompt learning.<n>We conduct experiments to evaluate the impact of various fl and prompt configurations, such as client scale, aggregation strategies, and prompt length.<n>We explore strategies for enhancing prompt learning in complex scenarios where label skew and domain shift coexist.
  arXiv  Detail & Related papers  (2025-05-29T03:09:15Z)
• Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models [79.90523648823522]
  Multi-stage continual learning can lead to catastrophic forgetting.<n>This paper evaluates three mitigation strategies-model merging, discounting the LoRA scaling factor, and experience replay.<n>Results show that experience replay is the most effective, with further gains achieved by combining it with other methods.
  arXiv  Detail & Related papers  (2025-05-23T05:50:14Z)
• DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation [59.79833777420334]
  Large language model (LLM) agents have shown promising performance in generating code for solving complex data science problems.<n>We develop a novel inference-time optimization framework, referred to as DSMentor, to enhance LLM agent performance.<n>Our work underscores the importance of developing effective strategies for accumulating and utilizing knowledge during inference.
  arXiv  Detail & Related papers  (2025-05-20T10:16:21Z)
• Enhancing LLM Knowledge Learning through Generalization [73.16975077770765]
  We show that an LLM's ability to continually predict the same factual knowledge tokens given diverse paraphrased contexts is positively correlated with its capacity to extract that knowledge via question-answering.<n>We propose two strategies to enhance LLMs' ability to predict the same knowledge tokens given varied contexts, thereby enhancing knowledge acquisition.
  arXiv  Detail & Related papers  (2025-03-05T17:56:20Z)
• RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation [46.237206695937246]
  We propose Retrieval-And-Structuring (RAS), a framework that dynamically constructs query-specific knowledge graphs.<n>On seven knowledge-intensive benchmarks, RAS consistently outperforms strong baselines.<n>Our results demonstrate that dynamic, query-specific knowledge structuring offers a robust path to improving reasoning accuracy and robustness in language model generation.
  arXiv  Detail & Related papers  (2025-02-16T05:01:49Z)
• MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct [148.39859547619156]
  We propose MMEvol, a novel multimodal instruction data evolution framework.<n>MMEvol iteratively improves data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution.<n>Our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-09T17:44:00Z)
• On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation [16.79923685316516]
  We explore three prompt construction protocols: Expert-guided, LLM-guided, and Novel-Mapping.<n>We find that context-enriched prompts lead to significantly improved data generation quality and training efficiency.
  arXiv  Detail & Related papers  (2024-09-06T00:02:09Z)
• Reasoning Factual Knowledge in Structured Data with Large Language Models [26.00548862629018]
  Large language models (LLMs) have made remarkable progress in various natural language processing tasks. Structured data possesses unique characteristics that differ from the unstructured texts used for pretraining. We propose a benchmark named StructFact to evaluate the structural reasoning capabilities of LLMs in inferring factual knowledge.
  arXiv  Detail & Related papers  (2024-08-22T08:05:09Z)
• Generative Multi-Modal Knowledge Retrieval with Large Language Models [75.70313858231833]
  We propose an innovative end-to-end generative framework for multi-modal knowledge retrieval. Our framework takes advantage of the fact that large language models (LLMs) can effectively serve as virtual knowledge bases. We demonstrate significant improvements ranging from 3.0% to 14.6% across all evaluation metrics when compared to strong baselines.
  arXiv  Detail & Related papers  (2024-01-16T08:44:29Z)
• Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning [37.22349652230841]
  Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt. In this paper, we demonstrate that factual knowledge is imperative for the performance of ICL in three core facets. We introduce a novel Knowledgeable In-Context Tuning (KICT) framework to further improve the performance of ICL.
  arXiv  Detail & Related papers  (2023-09-26T09:06:39Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)

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.