Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs

• URL: http://arxiv.org/abs/2606.29254v1
• Date: Sun, 28 Jun 2026 07:53:11 GMT
• Title: Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs
• Abstract summary: Large language models (LLMs) demonstrate broad reasoning abilities but struggle with accuracy and reliability in specialized domains such as travel.<n>We propose a modular pipeline for building a travel-domain reasoning LLM grounded in an expert-designed knowledge graph.<n>Our pipeline integrates a travel KG that encodes domain entities and their relationships, a supervised fine-tuning stage that embeds the domain knowledge into a reasoning-capable LLM.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) demonstrate broad reasoning abilities but struggle with accuracy and reliability in specialized domains such as travel, where reasoning depends on precise definitions, rules, and expert-defined conceptual frameworks, and where confident but unfounded outputs arise from a reasoning failure in which the model has not internalized the underlying domain graph rather than from missing domain knowledge alone. We propose a modular pipeline for building a travel-domain reasoning LLM grounded in an expert-designed knowledge graph (KG). Our pipeline integrates a travel KG that encodes domain entities and their relationships, a bottom-up construction procedure that walks the KG to produce multi-hop question answer (QA) pairs, a supervised fine-tuning stage that embeds the domain knowledge into a reasoning-capable LLM using the generated QA pairs as auditable reasoning traces, and a travel-domain benchmark dataset that measures the fine-tuned model's accuracy and calibration. We evaluate our approach using Qwen3-4B with LoRA adaptation. Our reasoning model achieves an $82.4\%$ exact match on the benchmark. This performance significantly outperforms the pretrained Qwen3-4B baseline at $22.4\%$. A calibration analysis decomposes the residual $17.57\%$ of errors into two distinct failure modes: an over-confident multi-label decoder that predicts both correct answers plus one spurious option on most dual-answer mistakes, and a smaller reasoning failure on single-answer questions where the supporting facts are present in the KG but the model fails to reconstruct the correct multi-hop path. This split confirms that explicit KG-grounded reasoning substantially improves the accuracy and uncertainty interpretation of LLMs in specialized domains, and isolates per-option calibration and trace-length-aware decoding as the next axes of improvement.

Related papers

• Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering [4.464939140209426]
  We propose a context-augmented training framework for multi-hop question-answering.<n>Although generally applicable, we validate the framework in the context of disease-specific knowledge graphs.<n>Across both diseases, context-augmented supervision consistently improves multi-hop performance over KG-only supervision.
  arXiv  Detail & Related papers  (2026-09-10T21:39:11Z)
• Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming [5.951101028540166]
  Chain-of-thought (CoT) prompting enables large language models to tackle multi-step reasoning tasks.<n>We present Reason Popper-ly, a neurosymbolic framework that uses inductive logic programming (ILP) to learn relation composition rules.
  arXiv  Detail & Related papers  (2026-07-25T03:24:05Z)
• Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals [75.25256166997414]
  We introduce Metacognition-as-Reward (MaR), a metacognition-inspired RL framework.<n>MaR guides reasoning through two general process dimensions.<n>MaR consistently improves model performance, achieving up to a 7.7% gain over the base model.
  arXiv  Detail & Related papers  (2026-05-22T08:54:37Z)
• Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution [12.955460962298588]
  We introduce Stepwise Confidence Attribution (SCA), a framework for closed-source LLMs that assigns step-level confidence based only on generated reasoning traces.<n>SCA reliably identifies low-confidence steps strongly correlated with reasoning errors.<n>Using step-level confidence to guide self-correction improves the correction success rate by up to 13.5% over answer-level feedback.
  arXiv  Detail & Related papers  (2026-05-19T00:57:51Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling [21.45871501724415]
  We propose a data-driven approach to automatically construct highly granular reasoning model error.<n>Rubrics can be used to build stronger LLM-as-judge reward functions.<n>This extension opens the door for teaching models to solve complex technical problems without a full dataset of gold labels.
  arXiv  Detail & Related papers  (2026-02-06T15:51:52Z)
• Hard Negative Sample-Augmented DPO Post-Training for Small Language Models [4.425580048633862]
  We propose a lightweight and pragmatic post-training pipeline that targets structured errors under realistic compute budgets.<n>We introduce a compact MathVerifier that decomposes a candidate solution into a six-dimensional error profile and aggregates it into interpretable wrongness and absurdity scores.<n> Experiments show that verifier-guided, weighted DPO yields more targeted improvements than vanilla SFT and unweighted DPO.
  arXiv  Detail & Related papers  (2025-12-17T06:15:52Z)
• Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs [85.37131922131657]
  We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs)<n>Even when these models know the correct answer, they frequently arrive there through incorrect reasoning paths.<n>We propose PSO (Path-Select Optimization), a two-stage post-training framework designed to enhance both the reasoning performance and stability of existing LVLMs.
  arXiv  Detail & Related papers  (2025-12-06T03:02:55Z)
• Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank [71.09032766271493]
  Large language models (LLMs) are prone to errors and hallucinations.<n>How to check their outputs effectively and efficiently has become a critical problem in their applications.
  arXiv  Detail & Related papers  (2025-10-28T11:01:10Z)
• FinReflectKG - MultiHop: Financial QA Benchmark for Reasoning with Knowledge Graph Evidence [0.0]
  We present FinReflectKG - MultiHop, a benchmark built on FinReflectKG, a temporally indexed financial Knowledge Graph.<n>We generate financial analyst style questions with exact supporting evidence from the KG.<n>Across both reasoning and non-reasoning models, KG-guided precise retrieval yields substantial gains.
  arXiv  Detail & Related papers  (2025-10-03T11:19:31Z)
• A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA [65.38186593873313]
  Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise.<n>We introduce a proof-of-concept multi-call framework for MHQA, InfoQA.<n>We construct a stringent and noise-rich benchmark to validate our theory and framework.
  arXiv  Detail & Related papers  (2025-09-25T14:11:57Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.931194824519935]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning [15.59540726867483]
  We argue that in guided decoding, assessing the potential of an incomplete reasoning path can be more advantageous than simply ensuring per-step correctness. Inspired by the findings that $textitoutcome supervision for guided decoding essentially acts as a value model, we propose Outcome-supervised Value Model (OVM) Our experiments on two multi-step mathematical reasoning datasets, GSM8K and Game of 24, demonstrate the superior performance of the OVM model.
  arXiv  Detail & Related papers  (2023-11-16T09:56:28Z)
• GRACE: Discriminator-Guided Chain-of-Thought Reasoning [75.35436025709049]
  We propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE) to steer the decoding process towards producing correct reasoning steps. GRACE employs a discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates.
  arXiv  Detail & Related papers  (2023-05-24T09:16:51Z)

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.