REVIEW 6 cited by
Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization of KG for large language models (LLMs) prevalently relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs' step-wise reasoning capabilities and KGs' structural nature. In this paper, we present DoG (Decoding on Graphs), a novel framework that facilitates a deep synergy between LLMs and KGs. We first define a concept, well-formed chain, which consists of a sequence of interrelated fact triplets on the KGs, starting from question entities and leading to answers. We argue that this concept can serve as a principle for making faithful and sound reasoning for KGQA. To enable LLMs to generate well-formed chains, we propose graph-aware constrained decoding, in which a constraint derived from the topology of the KG regulates the decoding process of the LLMs. This constrained decoding method ensures the generation of well-formed chains while making full use of the step-wise reasoning capabilities of LLMs. Based on the above, DoG, a training-free approach, is able to provide faithful and sound reasoning trajectories grounded on the KGs. Experiments across various KGQA tasks with different background KGs demonstrate that DoG achieves superior and robust performance. DoG also shows general applicability with various open-source LLMs.
Forward citations
Cited by 6 Pith papers
-
Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
Modeling agent trajectories as action-centric probabilistic graphs lets a GNN warn LLM agents of likely step-level errors before execution, improving pass ratio ~14.7% across four benchmarks.
-
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
BYOKG-RAG combines LLM-generated entities, paths, queries, and candidate answers with multiple graph retrieval tools to answer questions over custom knowledge graphs without training data.
-
RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning
RAG-Zeval uses rule-guided RL with ranking rewards on synthetic responses to train a 7B model that evaluates RAG faithfulness and correctness competitively with 70B-class judges.
-
Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA
RAR couples chain-of-thought reasoning with knowledge-graph-constrained path decoding and EM-style training, reporting 93.3 Hit@1 on WebQSP and 91.0 on CWQ.
-
From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
A review that organizes the knowledge graph and large language model integration field into three categories and argues for more attention to scalability, efficiency, and data quality.
-
LLM Inference Enhanced by External Knowledge: A Survey
A survey of methods that enhance LLM inference by integrating external structured knowledge from tables and knowledge graphs.
Discussion (0). Continue with ORCID to comment.