Improving Factuality with Explicit Working Memory

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Mingda, Li, Yang, Padthe, Karthik, Shao, Rulin, Sun, Alicia, Zettlemoyer, Luke, Ghosh, Gargi, Yih, Wen-tau
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909630839390208
author Chen, Mingda
Li, Yang
Padthe, Karthik
Shao, Rulin
Sun, Alicia
Zettlemoyer, Luke
Ghosh, Gargi
Yih, Wen-tau
author_facet Chen, Mingda
Li, Yang
Padthe, Karthik
Shao, Rulin
Sun, Alicia
Zettlemoyer, Luke
Ghosh, Gargi
Yih, Wen-tau
contents Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited by the traditional RAG design. To address these challenges, we introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The memory is refreshed based on online fact-checking and retrieval feedback, allowing EWE to rectify false claims during the generation process and ensure more accurate and reliable outputs. Our experiments demonstrate that Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 6 points absolute without sacrificing the helpfulness of the responses. Further analysis reveals that the design of rules for memory updates, configurations of memory units, and the quality of the retrieval datastore are crucial factors for influencing model performance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18069
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Factuality with Explicit Working Memory
Chen, Mingda
Li, Yang
Padthe, Karthik
Shao, Rulin
Sun, Alicia
Zettlemoyer, Luke
Ghosh, Gargi
Yih, Wen-tau
Computation and Language
Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited by the traditional RAG design. To address these challenges, we introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The memory is refreshed based on online fact-checking and retrieval feedback, allowing EWE to rectify false claims during the generation process and ensure more accurate and reliable outputs. Our experiments demonstrate that Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 6 points absolute without sacrificing the helpfulness of the responses. Further analysis reveals that the design of rules for memory updates, configurations of memory units, and the quality of the retrieval datastore are crucial factors for influencing model performance.
title Improving Factuality with Explicit Working Memory
topic Computation and Language
url https://arxiv.org/abs/2412.18069