Citation-Enhanced Generation for LLM-based Chatbots
- URL: http://arxiv.org/abs/2402.16063v3
- Date: Mon, 4 Mar 2024 01:53:35 GMT
- Title: Citation-Enhanced Generation for LLM-based Chatbots
- Authors: Weitao Li, Junkai Li, Weizhi Ma, Yang Liu
- Abstract summary: Large language models (LLMs) exhibit powerful general intelligence across diverse scenarios.
They may produce hallucinated content in responses, which significantly limits their applicability.
We propose a novel post-hoc Citation-Enhanced Generation approach combined with retrieval argumentation.
- Score: 11.973280288131225
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models (LLMs) exhibit powerful general intelligence across
diverse scenarios, including their integration into chatbots. However, a vital
challenge of LLM-based chatbots is that they may produce hallucinated content
in responses, which significantly limits their applicability. Various efforts
have been made to alleviate hallucination, such as retrieval augmented
generation and reinforcement learning with human feedback, but most of them
require additional training and data annotation. In this paper, we propose a
novel post-hoc Citation-Enhanced Generation (CEG) approach combined with
retrieval argumentation. Unlike previous studies that focus on preventing
hallucinations during generation, our method addresses this issue in a post-hoc
way. It incorporates a retrieval module to search for supporting documents
relevant to the generated content, and employs a natural language
inference-based citation generation module. Once the statements in the
generated content lack of reference, our model can regenerate responses until
all statements are supported by citations. Note that our method is a
training-free plug-and-play plugin that is capable of various LLMs. Experiments
on various hallucination-related datasets show our framework outperforms
state-of-the-art methods in both hallucination detection and response
regeneration on three benchmarks. Our codes and dataset will be publicly
available.
Related papers
- LargePiG: Your Large Language Model is Secretly a Pointer Generator [15.248956952849259]
We introduce relevance hallucination and factuality hallucination as a new typology for hallucination problems brought by query generation based on Large Language Models (LLMs)
We propose an effective way to separate content from form in LLM-generated queries, which preserves the factual knowledge extracted and integrated from the inputs and compiles the syntactic structure, including function words, using the powerful linguistic capabilities of the LLM.
arXiv Detail & Related papers (2024-10-15T07:41:40Z) - On the Capacity of Citation Generation by Large Language Models [38.47160164251295]
Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs)
arXiv Detail & Related papers (2024-10-15T03:04:26Z) - LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models [96.64960606650115]
LongHalQA is an LLM-free hallucination benchmark that comprises 6K long and complex hallucination text.
LongHalQA is featured by GPT4V-generated hallucinatory data that are well aligned with real-world scenarios.
arXiv Detail & Related papers (2024-10-13T18:59:58Z) - Analysis of Plan-based Retrieval for Grounded Text Generation [78.89478272104739]
hallucinations occur when a language model is given a generation task outside its parametric knowledge.
A common strategy to address this limitation is to infuse the language models with retrieval mechanisms.
We analyze how planning can be used to guide retrieval to further reduce the frequency of hallucinations.
arXiv Detail & Related papers (2024-08-20T02:19:35Z) - A Comprehensive Survey of Hallucination Mitigation Techniques in Large
Language Models [7.705767540805267]
Large Language Models (LLMs) continue to advance in their ability to write human-like text.
A key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded.
This paper presents a survey of over 32 techniques developed to mitigate hallucination in LLMs.
arXiv Detail & Related papers (2024-01-02T17:56:30Z) - AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall.
We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
arXiv Detail & Related papers (2023-09-30T05:20:02Z) - Trapping LLM Hallucinations Using Tagged Context Prompts [11.655802601887197]
We propose a novel method to recognize and flag instances when large language models perform outside their domain knowledge.
We find that the use of context combined with embedded tags can successfully combat hallucinations within generative language models.
arXiv Detail & Related papers (2023-06-09T17:48:54Z) - Active Retrieval Augmented Generation [123.68874416084499]
Augmenting large language models (LMs) by retrieving information from external knowledge resources is one promising solution.
Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input.
We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content.
arXiv Detail & Related papers (2023-05-11T17:13:40Z) - Recitation-Augmented Language Models [85.30591349383849]
We show that RECITE is a powerful paradigm for knowledge-intensive NLP tasks.
Specifically, we show that by utilizing recitation as the intermediate step, a recite-and-answer scheme can achieve new state-of-the-art performance.
arXiv Detail & Related papers (2022-10-04T00:49:20Z) - A Token-level Reference-free Hallucination Detection Benchmark for
Free-form Text Generation [50.55448707570669]
We propose a novel token-level, reference-free hallucination detection task and an associated annotated dataset named HaDes.
To create this dataset, we first perturb a large number of text segments extracted from English language Wikipedia, and then verify these with crowd-sourced annotations.
arXiv Detail & Related papers (2021-04-18T04:09:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.