Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specif...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHANG, Xuan, GAO, Wei
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9323
https://ink.library.smu.edu.sg/context/sis_research/article/10323/viewcontent/2024.lrec_main.1209_pvoa_cc_by.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10323
record_format dspace
spelling sg-smu-ink.sis_research-103232024-09-26T07:51:57Z Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM ZHANG, Xuan GAO, Wei Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents based on the non-retrieval ground truth of the task. We evaluate our model on two public datasets for real-world news claim verification, and the results demonstrate that FFRR achieves significant improvements over strong LLM-enabled and non-LLM baselines. 2023-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9323 https://ink.library.smu.edu.sg/context/sis_research/article/10323/viewcontent/2024.lrec_main.1209_pvoa_cc_by.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Claim Verification Reinforcement Retrieval Fine-Grained Feedbacks Large Language Model Artificial Intelligence and Robotics Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Claim Verification
Reinforcement Retrieval
Fine-Grained Feedbacks
Large Language Model
Artificial Intelligence and Robotics
Numerical Analysis and Scientific Computing
spellingShingle Claim Verification
Reinforcement Retrieval
Fine-Grained Feedbacks
Large Language Model
Artificial Intelligence and Robotics
Numerical Analysis and Scientific Computing
ZHANG, Xuan
GAO, Wei
Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM
description Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents based on the non-retrieval ground truth of the task. We evaluate our model on two public datasets for real-world news claim verification, and the results demonstrate that FFRR achieves significant improvements over strong LLM-enabled and non-LLM baselines.
format text
author ZHANG, Xuan
GAO, Wei
author_facet ZHANG, Xuan
GAO, Wei
author_sort ZHANG, Xuan
title Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM
title_short Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM
title_full Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM
title_fullStr Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM
title_full_unstemmed Reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with Black-Box LLM
title_sort reinforcement retrieval leveraging fine-grained feedback for fact checking news claims with black-box llm
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/9323
https://ink.library.smu.edu.sg/context/sis_research/article/10323/viewcontent/2024.lrec_main.1209_pvoa_cc_by.pdf
_version_ 1814047909455331328