paper-with-me

홈 › Papers

Advancing Large Language Model Attribution through Self-Improving

2024-10-17 · Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. However, improving this capability requires high-quality attribution data, which is costly and labor-intensive. Inspired by recent advances in self-improvement that enhance LLMs without manual annotation, we present START, a Self-Taught AttRibuTion framework for iteratively improving the attribution capability of LLMs. First, to prevent models from stagnating due to initially insufficient supervision signals, START leverages the model to self-construct synthetic training data for warming up. To further self-improve the model's attribution ability, START iteratively utilizes fine-grained preference supervision signals constructed from its sampled responses to encourage robust, comprehensive, and attributable generation. Experiments on three open-domain question-answering datasets, covering long-form QA and multi-step reasoning, demonstrate significant performance gains of 25.13% on average without relying on human annotations and more advanced models. Further analysis reveals that START excels in aggregating information across multiple sources.

📄 PDF Abstract BibTeX arXiv:2410.13298

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelOpen-Domain Question AnsweringQuestion Answering

Similar Papers 제목 키워드 기반

AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning

2022-10-12 · Tao Yang, Jinghao Deng, Xiaojun Quan, Qifan Wang 외

Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proport…

Language ModelingLanguage Modelling

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

2024-06-19 · Jirui Qi, Gabriele Sarti, Raquel Fernández, Arianna Bisazza

Ensuring the verifiability of model answers is a fundamental challenge for retrieval-augmented generation (RAG) in the question answering (QA) domain. Recently, self-citation prompting was proposed to make large language…

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images

2025-03-26 · CVPR 2025 1 · Tai D. Nguyen, Aref Azizpour, Matthew C. Stamm

The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional method…

AllForgery Image Detection

SX-GeoTree: Self-eXplaining Geospatial Regression Tree Incorporating the Spatial Similarity of Feature Attributions

2025-11-25 · Chaogui Kang, Lijian Luo, Qingfeng Guan, Yu Liu arxiv

Decision trees remain central for tabular prediction but struggle with (i) capturing spatial dependence and (ii) producing locally stable (robust) explanations. We present SX-GeoTree, a self-explaining geospatial regress…

Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs

2026-03-30 · Junsol Kim, Winnie Street, Roberta Rocca, Daine M. Korngiebel 외 arxiv

Safety fine-tuning in Large Language Models (LLMs) seeks to suppress potentially harmful forms of mind-attribution such as models asserting their own consciousness or claiming to experience emotions. We investigate wheth…