Paper 1（Main）
■書誌情報
Keito Sei, Sunil Kumar Maurya, Yohei Kobashi, Yutaka Matsuo: Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference, Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026), Main, November 2026
■概要
Graph-based retrieval is effective for knowledge graph question answering (KGQA), but retrieving the correct reasoning path remains challenging in multi-hop settings because the retrieval objective changes as reasoning progresses. Existing methods often address this issue with repeated LLM-based planning, which improves adaptivity but increases inference cost. We present a training-free residual-guided retrieval framework that updates the retrieval signal according to the current reasoning path in embedding space. The method performs multi-hop graph retrieval without repeated hop-wise LLM calls and invokes the LLM only once for final answer generation. Experiments on WebQSP and CWQ show that our method achieves superior Hit rates with only a single LLM call. Additional comparisons with supervised graph-based KGQA methods show that the proposed method remains effective without task-specific training data. These results suggest that residual-guided retrieval is an efficient alternative for multi-hop graph-based question answering.
Paper 2（Findings）
■書誌情報
Yingjian Chen, Haoran Liu, Yinhong Liu, Sherry T. Tong, Aosong Feng, Jinghui Lu, Juntao Zhang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li: From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs, Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026), Findings, November 2026
■概要
Large Language Models (LLMs) show strong reasoning ability in open-domain question answering, yet their reasoning processes are typically linear and often logically inconsistent. In contrast, real-world reasoning requires integrating multiple premises and solving subproblems in parallel. Existing methods, such as Chain-of-Thought (CoT), express reasoning in a linear textual form, which may appear coherent but frequently leads to inconsistent conclusions. Recent approaches rely on externally provided graphs and do not explore how LLMs can construct and use their own graph-structured reasoning, particularly in open-domain QA. To fill this gap, we novelly explore graph-structured reasoning of LLMs in general-domain question answering. We propose Self-Graph Reasoning (SGR), a framework that enables LLMs to explicitly represent their reasoning process as a structured graph before producing the final answer. We further construct a graph-structured reasoning dataset that merges multiple candidate reasoning graphs into refined graph structures for model training. Experiments on five QA benchmarks across both general and specialized domains show that SGR consistently improves reasoning consistency and yields a 17.74% gain over the base model. The LLaMA-3.3-70B model fine-tuned with SGR performs comparably to GPT-4o and surpasses Claude-3.5-Haiku, demonstrating the effectiveness of graph-structured reasoning.