paper-with-me

Papers

RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering

2026-01-27 · Kaehyun Um, KyuHwan Yeom, Haerim Yang, Minyoung Choi, Hyeongjun Yang, Kyong-Ho Lee arxiv

Large Language Models (LLMs) have recently demonstrated remarkable reasoning abilities, yet hallucinate on knowledge-intensive tasks. Retrieval-augmented generation (RAG) mitigates this issue by grounding answers in external sources, e.g., knowledge graphs (KGs). However, existing KG-based RAG approaches rely on semantics-unaware path sampling and are weakly aligned with KG reasoning objectives, which limits further accuracy gains. They also feed retrieved paths directly into the reasoner without organizing them into answer-centered reasoning paths, hindering small LLMs' ability to leverage the retrieved knowledge. Furthermore, prior works predominantly rely on large LLMs (e.g., ChatGPT/GPT-4) or assume backbones above 7B parameters, leaving sub-7B models underexplored. We address this gap with RPO-RAG, the first KG-based RAG framework specifically designed for small LLMs, to the best of our knowledge. RPO-RAG introduces three key innovations: (1) a query-path semantic sampling strategy that provides informative supervisory signals; (2) a relation-aware preference optimization that aligns training with intermediate KG reasoning signals (e.g., relation); and (3) an answer-centered prompt design that organizes entities and reasoning paths in an interpretable format. Extensive experiments on two benchmark Knowledge Graph Question Answering (KGQA) datasets, WebQSP and CWQ, demonstrate that RPO-RAG effectively bridges the performance gap between small and large language models. On WebQSP, it improves F1 by up to 8.8%, reflecting enhanced answer precision, while on CWQ it achieves new state-of-the-art results among models under 8B parameters in both Hit and F1. Overall, RPO-RAG substantially improves the reasoning capability of small LLMs, even under 3B parameters-highlighting their potential for resource-efficient and practical on-device KGQA applications.

📄 PDF Abstract BibTeX arXiv:2601.19225

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Question AnsweringKnowledge Graphs

Similar Papers 제목 키워드 기반

Aligning Large Language Models with Self-generated Preference Data

2024-06-06 · Dongyoung Kim, Kimin Lee, Jinwoo Shin, Jaehyung Kim

Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle…

In-Context Learning

On Diversified Preferences of Large Language Model Alignment

2023-12-12 · Dun Zeng, Yong Dai, Pengyu Cheng, Longyue Wang 외

Aligning large language models (LLMs) with human preferences has been recognized as the key to improving LLMs' interaction quality. However, in this pluralistic world, human preferences can be diversified due to annotato…

Language ModelingLanguage ModellingLarge Language Model

Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium

2025-03-14 · Kaizhao Liu, Qi Long, Zhekun Shi, Weijie J. Su 외

Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental …

Fairness

Can LLMs Capture Human Preferences?

2023-05-04 · Ali Goli, Amandeep Singh

We explore the viability of Large Language Models (LLMs), specifically OpenAI's GPT-3.5 and GPT-4, in emulating human survey respondents and eliciting preferences, with a focus on intertemporal choices. Leveraging the ex…

Benchmarking

Towards a Unified View of Preference Learning for Large Language Models: A Survey

2024-09-04 · Bofei Gao, Feifan Song, Yibo Miao, Zefan Cai 외

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small…