Knowledge_Graph
-
Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement
2026-04-16 08:02:55Midan Shim, Seokju Hwang, Kaehyun Um, Kyong-Ho LeeAbstract
Large language models still struggle with faithfulness and hallucinations despite their remarkable reasoning abilities. In Knowledge Graph Question Answering (KGQA), semantic parsing-based approaches address the limitations by understanding constraints in a user's question and converting them into a logical form to execute on a knowledge graph. However, existing KGQA benchmarks and methods are biased toward positive and calculation constraints. Negative constraints are neglected, although they frequently appear in real-world questions. In this paper, we introduce a new task, NEgative-conSTrained (NEST) KGQA, where each question contains at least one negative constraint, and a corresponding dataset, NestKGQA. We also design PyLF, a Python-formatted logical form, since existing logical forms are hardly suitable to express negation clearly while maintaining readability. Furthermore, NEST questions naturally contain multiple constraints. To mitigate their semantic complexity, we present a novel framework named CUCKOO, specialized to multiple-constrained questions and ensuring semantic executability. CUCKOO first generates a constraint-aware logical form draft and performs schema-guided semantic matching. It then selectively applies self-directed refinement only when executing improper logical forms yields an empty result, reducing cost while improving robustness. Experimental results demonstrate that CUCKOO consistently outperforms baselines on both conventional KGQA and NEST-KGQA benchmarks under few-shot settings.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14749
PDF
-
HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
2026-04-16 01:05:19Pranav YadavAbstract
Retrieval Augmented Generation (RAG) has proven to be a widely successful process at improving the quality of outputs from a Large Language Model (LLM) for wider context. However, RAG systems typically retrieve context from flat document stores, which struggles when queries require hierarchical or relational reasoning across structured knowledge. I present HG-RAG (Hierarchy-Guided RAG), a framework that performs graph-traversal over a hierarchical knowledge graph to deliver structured context to a language model. My retrieval pipeline resolves a named entity anchor from the query, then expands context upward through parent nodes, laterally through relational neighbors, and downward through child nodes when needed. I evaluate HG-RAG against a dense retrieval baseline across three world scales (18-800 nodes) with four query types: local fact, hierarchical, neighborhood, and multi-hop. Results show HG-RAG consistently outperforms the flat baseline on hierarchical, relational, and multi-hop reasoning tasks, while reducing hallucination and maintaining locality coherence.
Abstract (translated)
URL
https://arxiv.org/abs/2607.14095
PDF
-
Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
2026-04-15 17:43:10Zipeng Ling, Shuliang Liu, Shenghong Fu, Yuehao Tang, Seonil Son, Yao Wan, Xuming HuAbstract
LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sample. A natural approach would be to provide ground-truth labels to guide LLMs' reasoning. Contrary to intuition, we show that this yields no improvement in reasoning ability. We then propose CRAFT, a unified framework that mitigates both types of Step flaws, which builds a Reasoning Knowledge Graph (RKG) based on the consensus parts of multiple candidate traces, and synthesizes a high-quality trace through topological generation. Our approach improves label-prediction accuracy by 10+% on average, and consistently outperforms all baselines across both logical and mathematical reasoning benchmarks. Further, detailed benchmark evaluation proves that our method also improves the quality of LLMs' reasoning traces in multiple dimensions.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14121
PDF
-
Agentic GraphRAG: Navigating Unstructured Financial Data with Collaborative AI
2026-04-15 16:16:14Arthur Capozzi, Dirk HelbingAbstract
We present a collaborative agentic GraphRAG framework for expert analysis of commercial registry data. Public registries are often formally accessible, yet difficult to use in practice because they combine structured records with large volumes of unstructured legal text. This limits conventional keyword and vector-only retrieval, especially for multi-hop, temporal, and entity-centric investigations. Our approach builds a Neo4j knowledge graph through a three-phase pipeline: (i) deterministic ingestion of strong nodes from verified structured fields, (ii) LLM-based extraction of weak nodes from unstructured notices, and (iii) deterministic identity resolution and deduplication. On top of this graph, we introduce an analytical modular agent that integrates zero-shot intent routing, a bounded reflection loop, secure tool-mediated graph access, and state-aware response synthesis. A human-in-the-loop dashboard exposes evidence and execution traces to support transparency and auditability. We evaluate the framework on the Swiss Official Gazette of Commerce, a multilingual corpus of more than seven million publications over seven years. We further contribute a multi-tier evaluation protocol covering entity-resolution precision, tool-routing behavior, answer quality, and multi-turn conversational performance. Across automated, human-curated, and conversational benchmarks, the proposed agentic GraphRAG system consistently outperforms a standard agentic vector-RAG baseline, with strong gains in correctness, answer relevance, information recall, turn success rate, and context carryover accuracy. The architecture is modular, reproducible, and transferable to other commercial gazettes and public-sector registry systems.
Abstract (translated)
URL
https://arxiv.org/abs/2605.18770
PDF
-
Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs
2026-04-15 15:25:25Hussein Abdallah, Ibrahim Abdelaziz, Panos Kalnis, Essam MansourAbstract
Open-world Question Answering (OW-QA) over knowledge graphs (KGs) aims to answer questions over incomplete or evolving KGs. Traditional KGQA assumes a closed world where answers must exist in the KG, limiting real-world applicability. In contrast, open-world QA requires inferring missing knowledge based on graph structure and context. Large language models (LLMs) excel at language understanding but lack structured reasoning. Graph neural networks (GNNs) model graph topology but struggle with semantic interpretation. Existing systems integrate LLMs with GNNs or graph retrievers. Some support open-world QA but rely on structural embeddings without semantic grounding. Most assume observed paths or complete graphs, making them unreliable under missing links or multi-hop reasoning. We present GLOW, a hybrid system that combines a pre-trained GNN and an LLM for open-world KGQA. The GNN predicts top-k candidate answers from the graph structure. These, along with relevant KG facts, are serialized into a structured prompt (e.g., triples and candidates) to guide the LLM's reasoning. This enables joint reasoning over symbolic and semantic signals, without relying on retrieval or fine-tuning. To evaluate generalization, we introduce GLOW-BENCH, a 1,000-question benchmark over incomplete KGs across diverse domains. GLOW outperforms existing LLM-GNN systems on standard benchmarks and GLOW-BENCH, achieving up to 53.3% and an average 38% improvement. GitHub code and data are available.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13979
PDF
-
MCPThreatHive: Automated Threat Intelligence for Model Context Protocol Ecosystems
2026-04-15 13:19:22Yi Ting Shen, Kentaroh Toyoda, Alex LeungAbstract
The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing frameworks are inadequately equipped to address. We present MCPThreatHive, an open-source platform that automates the end-to-end lifecycle of MCP threat intelligence: from continuous, multi-source data collection through AI-driven threat extraction and classification, to structured knowledge graph storage and interactive visualization. The platform operationalizes the MCP-38 threat taxonomy, a curated set of 38 MCP-specific threat patterns mapped to STRIDE, OWASP Top 10 for LLM Applications, and OWASP Top 10 for Agentic Applications. A composite risk scoring model provides quantitative prioritization. Through a comparative analysis of representative existing MCP security tools, we identify three critical coverage gaps that MCPThreatHive addresses: incomplete compositional attack modeling, absence of continuous threat intelligence, and lack of unified multi-framework classification.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13849
PDF
-
Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate
2026-04-15 06:54:27Cunda Wang, Ziying Ma, Po Hu, Weihua Wang, Feilong BaoAbstract
Entity alignment (EA) aims to identify entities referring to the same real-world object across different knowledge graphs (KGs). Recent approaches based on large language models (LLMs) typically obtain entity embeddings through knowledge representation learning and use embedding similarity to identify an alignment-uncertain entity set. For each uncertain entity, a candidate entity set (CES) is then retrieved based on embedding similarity to support subsequent alignment reasoning and decision making. However, the reliability of the CES and the reasoning capability of LLMs critically affect the effectiveness of subsequent alignment decisions. To address this issue, we propose AgentEA, a reliable EA framework based on multi-agent debate. AgentEA first improves embedding quality through entity representation preference optimization, and then introduces a two-stage multi-role debate mechanism consisting of lightweight debate verification and deep debate alignment to progressively enhance the reliability of alignment decisions while enabling more efficient debate-based reasoning. Extensive experiments on public benchmarks under cross-lingual, sparse, large-scale, and heterogeneous settings demonstrate the effectiveness of AgentEA.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13551
PDF
-
QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence
2026-04-14 15:17:21Zhichao Lin, Zhichao Liang, Gaoqiang Liu, Meng Xu, Baoyu Xiang, Jian Xu, Guanjun JiangAbstract
As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this end, building upon Tongyi DeepResearch, a powerful agentic foundation model, we focus on the Chinese medical deep search scenario and propose QuarkMedSearch, systematically exploring a full-pipeline approach spanning medical multi-hop data construction, training strategies, and evaluation benchmarks to further push and assess its performance upper bound in vertical domains. Specifically, for data synthesis, to address the scarcity of deep search training data in the medical domain, we combine a large-scale medical knowledge graph with real-time online exploration to construct long-horizon medical deep search training data; for post-training, we adopt a two-stage SFT and RL training strategy that progressively enhances the model's planning, tool invocation, and reflection capabilities required for deep search, while maintaining search efficiency; for evaluation, we collaborate with medical experts to construct the QuarkMedSearch Benchmark through rigorous manual verification. Experimental results demonstrate that QuarkMedSearch achieves state-of-the-art performance among open-source models of comparable scale on the QuarkMedSearch Benchmark, while also maintaining strong competitiveness on general benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12867
PDF
-
Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs
2026-04-14 12:21:15Alkid Baci, Luke Friedrichs, Caglar Demir, N'Dah Jean Kouagou, Axel-Cyrille Ngonga NgomoAbstract
Knowledge graph embedding (KGE) models perform well on link prediction but struggle with unseen entities, relations, and especially literals, limiting their use in dynamic, heterogeneous graphs. In contrast, pretrained large language models (LLMs) generalize effectively through prompting. We reformulate link prediction as a prompt learning problem and introduce RALP, which learns string-based chain-of-thought (CoT) prompts as scoring functions for triples. Using Bayesian Optimization through MIPRO algorithm, RALP identifies effective prompts from fewer than 30 training examples without gradient access. At inference, RALP predicts missing entities, relations or whole triples and assigns confidence scores based on the learned prompt. We evaluate on transductive, numerical, and OWL instance retrieval benchmarks. RALP improves state-of-the-art KGE models by over 5% MRR across datasets and enhances generalization via high-quality inferred triples. On OWL reasoning tasks with complex class expressions (e.g., $\exists this http URL$, $\geq 5 \; this http URL$), it achieves over 88% Jaccard similarity. These results highlight prompt-based LLM reasoning as a flexible alternative to embedding-based methods. We release our implementation, training, and evaluation pipeline as open source: this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2604.12651
PDF
-
Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
2026-04-14 09:27:52Shuai Wang, Xixi Wang, Yinan YuAbstract
Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question Answering (KBQA) mitigates this by grounding generation in Knowledge Graphs (KGs). However, most multi-hop KBQA methods rely on explicit edge traversal, making them fragile to KG incompleteness. In this paper, we proposed a novel graph-based soft prompting framework that shifts the reasoning paradigm from node-level path traversal to subgraph-level reasoning. Specifically, we employ a Graph Neural Network (GNN) to encode extracted structural subgraphs into soft prompts, enabling LLM to reason over richer structural context and identify relevant entities beyond immediate graph neighbors, thereby reducing sensitivity to missing edges. Furthermore, we introduce a two-stage paradigm that reduces computational cost while preserving good performance: a lightweight LLM first leverages the soft prompts to identify question-relevant entities and relations, followed by a more powerful LLM for evidence-aware answer generation. Experiments on four multi-hop KBQA benchmarks show that our approach achieves state-of-the-art performance on three of them, demonstrating its effectiveness. Code is available at the repository: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12503
PDF
-
KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
2026-04-14 09:14:21Shuai Wang, Yinan YuAbstract
Large Language Models (LLMs) exhibit strong abilities in natural language understanding and generation, yet they struggle with knowledge-intensive reasoning. Structured Knowledge Graphs (KGs) provide an effective form of external knowledge representation and have been widely used to enhance performance in classical Knowledge Base Question Answering (KBQA) tasks. However, performing precise multi-hop reasoning over KGs for complex queries remains highly challenging. Most existing approaches decompose the reasoning process into a sequence of isolated steps executed through a fixed pipeline. While effective to some extent, such designs constrain reasoning flexibility and fragment the overall decision process, often leading to incoherence and the loss of critical intermediate information from earlier steps. In this paper, we introduce KG-Reasoner, an end-to-end framework that integrates multi-step reasoning into a unified "thinking" phase of a Reasoning LLM. Through Reinforcement Learning (RL), the LLM is trained to internalize the KG traversal process, enabling it to dynamically explore reasoning paths, and perform backtracking when necessary. Experiments on eight multi-hop and knowledge-intensive reasoning benchmarks demonstrate that KG-Reasoner achieves competitive or superior performance compared to the state-of-the-art methods. Codes are available at the repository: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12487
PDF
-
AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs
2026-04-14 01:17:24Manoj Madushanka Perera, Adnan Mahmood, Kasun Eranda Wijethilake, Quan Z. ShengAbstract
Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluating short- and long-term memories remain difficult due to the absence of datasets that encode both short- and long-term conversational history. Existing conversational datasets lack memory grounding, overlook topic continuity, or rely on costly human annotation. To address these gaps, we introduce AgenticAI-DialogGen, a modular agent-based framework that generates persona-grounded and topic-guided conversations without human supervision. The framework uses LLM agents to extract knowledge graphs, identify topics, build speaker personas, and simulate topic-guided conversations from unstructured conversations. A QA module generates memory-grounded Question Answer (QA) pairs drawn from short- and long-term conversational histories. We also generated a new dataset entitled, TopicGuidedChat (TGC), where long-term memory is encoded as speaker-specific knowledge graphs and short-term memory as newly generated topic-guided conversations. Evaluations depict that AgenticAI-DialogGen yields higher conversational quality and LLMs fine-tuned on TGC dataset achieve improved performance on memory-grounded QA tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12179
PDF
-
Policy-Invisible Violations in LLM-Based Agents
2026-04-14 01:15:15Jie Wu, Ming GongAbstract
LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational policy because the facts needed for correct policy judgment are hidden at decision time. We call this failure mode policy-invisible violations: cases in which compliance depends on entity attributes, contextual state, or session history absent from the agent's visible context. We present PhantomPolicy, a benchmark spanning eight violation categories with balanced violation and safe-control cases, in which all tool responses contain clean business data without policy metadata. We manually review all 600 model traces produced by five frontier models and evaluate them using human-reviewed trace labels. Manual review changes 32 labels (5.3%) relative to the original case-level annotations, confirming the need for trace-level human review. To demonstrate what world-state-grounded enforcement can achieve under favorable conditions, we introduce Sentinel, an enforcement framework based on counterfactual graph simulation. Sentinel treats every agent action as a proposed mutation to an organizational knowledge graph, performs speculative execution to materialize the post-action world state, and verifies graph-structural invariants to decide Allow/Block/Clarify. Against human-reviewed trace labels, Sentinel substantially outperforms a content-only DLP baseline (68.8% vs. 93.0% accuracy) while maintaining high precision, though it still leaves room for improvement on certain violation categories. These results demonstrate what becomes achievable once policy-relevant world state is made available to the enforcement layer.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12177
PDF
-
DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness
2026-04-13 16:38:36Javad M Alizadeh, Genhui Zheng, Chiu C Tan, Yuzhou Chen, Omar Martinez, Philip McCallion, Ying Ding, Chenguang Yang, AnneMarie Tomosky, Huanmei WuAbstract
People experiencing homelessness (PEH) face substantial barriers to accessing timely, accurate information about community services. DreamKG addresses this through a knowledge graph-augmented conversational system that grounds responses in verified, up-to-date data about Philadelphia organizations, services, locations, and hours. Unlike standard large language models (LLMs) prone to hallucinations, DreamKG combines Neo4j knowledge graphs with structured query understanding to handle location-aware and time-sensitive queries reliably. The system performs spatial reasoning for distance-based recommendations and temporal filtering for operating hours. Preliminary evaluation shows 59% superiority over Google Search AI on relevant queries and 84% rejection of irrelevant queries. This demonstration highlights the potential of hybrid architectures that combines LLM flexibility with knowledge graph reliability to improve service accessibility for vulnerable populations effectively.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11703
PDF
-
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
2026-04-13 14:35:47Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang, Tiejun Ma, Yiwen GuoAbstract
Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing approaches model time as discrete metadata, either sorting by recency (burying old-yet-permanent knowledge), simply overwriting outdated facts, or requiring an expensive LLM call at every ingestion step, leaving them unable to distinguish persistent facts from evolving ones. To address this, we introduce RoMem, a drop-in temporal knowledge graph module for structured memory systems, applicable to agentic memory and beyond. A pretrained Semantic Speed Gate maps each relation's text embedding to a volatility score, learning from data that evolving relations (e.g., "president of") should rotate fast while persistent ones (e.g., "born in") should remain stable. Combined with continuous phase rotation, this enables geometric shadowing: obsolete facts are rotated out of phase in complex vector space, so temporally correct facts naturally outrank contradictions without deletion. On temporal knowledge graph completion, RoMem achieves state-of-the-art results on ICEWS05-15 (72.6 MRR). Applied to agentic memory, it delivers 2-3x MRR and answer accuracy on temporal reasoning (MultiTQ), dominates hybrid benchmark (LoCoMo), preserves static memory with zero degradation (DMR-MSC), and generalises zero-shot to unseen financial domains (FinTMMBench).
Abstract (translated)
URL
https://arxiv.org/abs/2604.11544
PDF
-
Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval
2026-04-13 13:02:44Dzenan Hamzic, Florian Skopik, Max Landauer, Markus Wurzenberger, Andreas RauberAbstract
Cyber threat intelligence (CTI) analysts must answer complex questions over large collections of narrative security reports. Retrieval-augmented generation (RAG) systems help language models access external knowledge, but traditional vector retrieval often struggles with queries that require reasoning over relationships between entities such as threat actors, malware, and vulnerabilities. This limitation arises because relevant evidence is often distributed across multiple text fragments and documents. Knowledge graphs address this challenge by enabling structured multi-hop reasoning through explicit representations of entities and relationships. However, multiple retrieval paradigms, including graph-based, agentic, and hybrid approaches, have emerged with different assumptions and failure modes. It remains unclear how these approaches compare in realistic CTI settings and when graph grounding improves performance. We present a systematic evaluation of four RAG architectures for CTI analysis: standard vector retrieval, graph-based retrieval over a CTI knowledge graph, an agentic variant that repairs failed graph queries, and a hybrid approach combining graph queries with text retrieval. We evaluate these systems on 3,300 CTI question-answer pairs spanning factual lookups, multi-hop relational queries, analyst-style synthesis questions, and unanswerable cases. Results show that graph grounding improves performance on structured factual queries. The hybrid graph-text approach improves answer quality by up to 35 percent on multi-hop questions compared to vector RAG, while maintaining more reliable performance than graph-only systems.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11419
PDF
-
PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers
2026-04-13 11:07:08Lei Xiong, Huaying Yuan, Zheng Liu, Zhao Cao, Zhicheng DouAbstract
Leveraging Multi-modal Large Language Models (MLLMs) to accelerate frontier scientific research is promising, yet how to rigorously evaluate such systems remains unclear. Existing benchmarks mainly focus on single-document understanding, whereas real scientific workflows require integrating evidence from multiple papers, including their text, tables, and figures. As a result, multi-modal, multi-document scientific reasoning remains underexplored and lacks systematic evaluation. To address this gap, we introduce PaperScope, a multi-modal multi-document benchmark designed for agentic deep research. PaperScope presents three advantages: (1) Structured scientific grounding. It is built on a knowledge graph of over 2,000 AI papers spanning three years, providing a structured foundation for research-oriented queries. (2) Semantically dense evidence construction. It integrates semantically related key information nodes and employs optimized random-walk article selector to sample thematically coherent paper sets, thereby ensuring adequate semantic density and task complexity. (3) Multi-task evaluation of scientific reasoning. It contains over 2,000 QA pairs across reasoning, retrieval, summarization, and problem solving, enabling evaluation of multi-step scientific reasoning. Experimental results show that even advanced systems such as OpenAI Deep Research and Tongyi Deep Research achieve limited scores on PaperScope, highlighting the difficulty of long-context retrieval and deep multi-source reasoning. PaperScope thus provides a rigorous benchmark alongside a scalable pipeline for constructing large-scale multi-modal, multi-source deep research datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11307
PDF
-
Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
2026-04-13 09:05:04Tianzhe Zhao, Jiaoyan Chen, Shuxiu Zhang, Haiping Zhu, Qika Lin, Jun LiuAbstract
Large language models (LLMs) have achieved remarkable success across a wide range of applications especially when augmented by external knowledge through retrieval-augmented generation (RAG). Despite their widespread adoption, recent studies have shown that LLMs often struggle to perform faithful reasoning when conflicting knowledge is retrieved. However, existing work primarily focuses on conflicts between external knowledge and the parametric knowledge of LLMs, leaving conflicts across external knowledge largely unexplored. Meanwhile, modern RAG systems increasingly emphasize the integration of unstructured text and (semi-)structured data like knowledge graphs (KGs) to improve knowledge completeness and reasoning faithfulness. To address this gap, we introduce ConflictQA, a novel benchmark that systematically instantiates conflicts between textual evidence and KG evidence. Extensive evaluations across representative LLMs reveal that, facing such cross-source conflicts, LLMs often fail to identify reliable evidence for correct reasoning. Instead, LLMs become more sensitive to prompting choices and tend to rely exclusively on either KG or textual evidence, resulting in incorrect responses. Based on these findings, we further propose XoT, a two-stage explanation-based thinking framework tailored for reasoning over heterogeneous conflicting evidence, and verify its effectiveness with extensive experiments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11209
PDF
-
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
2026-04-13 08:49:39Yingxu Wang, Jiaxin Huang, Mengzhu Wang, Nan YinAbstract
Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration. To address these challenges, we propose Trajectoryaware Reasoning with Adaptive Context and Exploration priors (TRACE), an experiential framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance the coherence and robustness of multihop KGQA. Specifically, TRACE dynamically translates evolving reasoning paths into natural language narratives to maintain semantic continuity, while abstracting prior exploration trajectories into reusable experiential priors that capture recurring exploration patterns. A dualfeedback re-ranking mechanism further integrates contextual narratives with exploration priors to guide relation selection during reasoning. Extensive experiments on multiple KGQA benchmarks demonstrate that TRACE consistently outperforms state-of-the-art baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11193
PDF
-
Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds
2026-04-13 07:20:21Pierre Jourlin (LIA)Abstract
This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation framework integrating two external benchmarks (DocRED, HotpotQA), WebQuestionsSP-style synthetic data, and the RAGAS evaluation framework in an automated pipeline. On 500 document-level relations, our system achieves an F1 of 0.70 $\pm$ 0.041 in zero-shot, compared to 0.80 for supervised DREEAM. Text-to-query achieves an accuracy of 0.80 $\pm$ 0.06 on 200 samples. Multi-hop reasoning achieves an Exact Match (EM) of 0.46$\pm$0.04 on 500 HotpotQA questions, with a RAGAS faithfulness of 0.96 $\pm$ 0.04 on 50 samples. Beyond the pipeline, we study diversity mechanisms for difficult multi-hop reasoning. On 181 questions unsolvable at zero temperature, self-consistency (k=5, T =0.7) recovers up to 23% EM with a single Mixture-of-Experts (MoE) model, but the cross-model oracle (3 architectures x 5 samples) reaches 46.4%. We highlight an agreement paradox: strong consensus among samples signals collective hallucination rather than a reliable answer, echoing the work of Moussa{ï}d et al. on the wisdom of crowds. Extending to the full pipeline (500 questions), self-consistency (k=3) raises EM from 0.46 to 0.48 $\pm$ 0.04. A confidence-routing cascade mechanism (Phi-4 $\rightarrow$ GPT-OSS, k=5) achieves an EM of 0.55 $\pm$ 0.04, the best result obtained, with 45.4% of questions rerouted. Finally, we show that V3 prompt engineering applied to other models does not reproduce the gains observed with Gemma-4, confirming the specific prompt/model interaction. The entire system runs in $\sim$5 h on a single RTX 3090, without any training, for an estimated carbon footprint of 0.09 kg CO2 eq.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11104
PDF
