2026· Annual Meeting of the Association for Computational Linguistics· pp. 45036-45054· 0 citations· 42 references
Computer Science
TL;DR
The proposed DR 2 identifies and localizes non-deterministic reasoning behaviors, uncovering the underlying semantic representation deficiencies in LLMs, and designs abductive reasoning-based preference learning, which promotes fine-grained semantic discrimination and mitigates non-deterministic reasoning errors.
Abstract
Large language models (LLMs) have demonstrated increasingly strong reasoning capabilities, achieving remarkable progress in knowledge graph question answering (KGQA). However, a key challenge in such systems is non-deterministic reasoning, where the model indecisively activates multiple semantically related knowledge graph edges for a given query, frequently leading to incorrect answers. To address this issue, we propose D iagnosing and R emedying Representation Deficiencies for D eterministic R easoning in KGQA (DR 2 ). DR 2 identifies and localizes non-deterministic reasoning behaviors, uncovering the underlying semantic representation deficiencies in LLMs. Building on this diagnosis, we design abductive reasoning-based preference learning, which promotes fine-grained semantic discrimination and mitigates non-deterministic reasoning errors. Experimental results demonstrate that the proposed DR 2 significantly outperforms several strong baselines, achieving state-of-the-art performance on the widely used WebQSP and CWQ benchmarks.Our code and data is available at https://github.com/HITlgw/DR2.
PYTHIA is presented, a training-free, plug-and-play solution for KGQA over any RDF KG which consists of an LLM agent guided by a relation-centric conceptual model of the KGQA task which is acted upon through a suite of tools for entity linking, graph exploration and query execution.
Sergios-Anestis Kefalidis, Konstantinos Plas, Manolis Koubarakis· Proceedings of the 32nd ACM...· 0 citations
Large language models are increasingly used for knowledge graph question answering (KGQA), but can fail to correctly ground answers in the underlying graph. Current approaches to LLM-based KGQA either rely on full semantic parsing into executable queries such as SPARQL, which is brittle in practice due to complex schemas or incompleteness of real-world KGs, or on LLM-reasoning and answer generation over KGs, which can be more robust but lacks formal guarantees. In this work, we study a complementary setting in which \emph{candidate} answers are generated by an LLM-based system and subsequently verified using lightweight symbolic constraints derived from the question. We introduce \emph{Constrained Entity Selection under Partial Knowledge (CES-PK)}, a problem formulation that focuses on eliminating invalid answers and providing symbolic support for valid ones without requiring construction of executable logical forms. To account for incomplete KGs, we employ a three-valued constraint semantics (\emph{satisfied, violated, unknown}) that avoids incorrect rejections under open-world assumptions. To demonstrate the effects of our method, we instantiate this framework over the Hetionet biomedical knowledge graph and evaluate the impact of type, relation, and exclusion constraints. Experiments show that precision improves by filtering invalid candidates, while recall is preserved due to retaining candidates whose constraints are not explicitly violated. Satisfied constraints provide additional positive symbolic evidence to rank remaining candidates.
E. Kitzelmann· Deutsche Jahrestagung für Kü...· 0 citations
The development of large language models (LLMs) has introduced innovative solutions to unsupervised knowledge graph question answering (KGQA). Existing methods typically retrieve answer entities by measuring semantic similarity between questions with reasoning paths in the KG. However, this paradigm struggles to capture the sequential dependencies embedded in the relational chains of complex questions. To bridge this gap, this paper proposes JPRQA, a Joint Progressive Reasoning Framework for unsupervised KGQA with LLMs, which decouples complex questions into sub‐questions to facilitate precise step‐by‐step reasoning over KG. Specifically, we designed a relation‐guided progressive reasoning (RPR) mechanism that leverages position‐aware relation predictors to model the sequential order of relations and perform step‐by‐step reasoning. Furthermore, we enhance answer retrieval through collaborative path optimization, which integrates LLMs with RPR to refine and identify optimal retrieval paths for questions. Experimental results demonstrate that JPRQA achieves an increase in F1 scores by 6.9 and 11.68 on the MetaQA (39,093 questions) and GrailQA (6763 questions) datasets, respectively, compared to other unsupervised methods.
Lite-CoNER is proposed, a lightweight NER framework that achieves an effective balance between recognition accuracy and inference efficiency and provides a transparent view of the decision-making process, proving that lightweight models can effectively inherit complex logic through structured distillation.
Yang Wang, Lushuang Gao· International Conference on...· 0 citations
This work proposes MARS, a scalable knowledge graph question answering (KGQA) approach that requires no model fine-tuning, and performs a structured retrieval procedure that links question entities to the KG and iteratively retrieves relevant next-hop information.
Nikit Srivastava, Daniel Vollmers, René Speck et al.· arXiv.org· 0 citations
TKFQA, a factuality consistency benchmark comprising 10,130 question-answering (QA) pairs grounded in tables, texts, and knowledge graphs, is introduced and ORLF, an LLM-agnostic training framework that models cross-context topological relations through knowledge-specific latent vectors is proposed.
Shibo Chu, Yuze Liu, Tiehua Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
