DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection
- URL: http://arxiv.org/abs/2402.10426v2
- Date: Fri, 5 Jul 2024 00:59:45 GMT
- Title: DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection
- Authors: Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, Minnan Luo,
- Abstract summary: Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles.
We propose Dell that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline.
- Score: 50.805599761583444
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount. In this work, we propose DELL that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline: 1) LLMs could \emph{generate news reactions} to represent diverse perspectives and simulate user-news interaction networks; 2) LLMs could \emph{generate explanations} for proxy tasks (e.g., sentiment, stance) to enrich the contexts of news articles and produce experts specializing in various aspects of news understanding; 3) LLMs could \emph{merge task-specific experts} and provide an overall prediction by incorporating the predictions and confidence scores of varying experts. Extensive experiments on seven datasets with three LLMs demonstrate that DELL outperforms state-of-the-art baselines by up to 16.8\% in macro f1-score. Further analysis reveals that the generated reactions and explanations are greatly helpful in misinformation detection, while our proposed LLM-guided expert merging helps produce better-calibrated predictions.
Related papers
- Potential and Perils of Large Language Models as Judges of Unstructured Textual Data [0.631976908971572]
This research investigates the effectiveness of LLM-as-judge models to evaluate the thematic alignment of summaries generated by other LLMs.
Our findings reveal that while LLM-as-judge offer a scalable solution comparable to human raters, humans may still excel at detecting subtle, context-specific nuances.
arXiv Detail & Related papers (2025-01-14T14:49:14Z) - Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
Large language models (LLMs) generate content that can undermine trust in online discourse.
Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-LLM collaboration.
To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
arXiv Detail & Related papers (2024-10-18T08:14:10Z) - PromptExp: Multi-granularity Prompt Explanation of Large Language Models [16.259208045898415]
We introduce PromptExp, a framework for multi-granularity prompt explanations by aggregating token-level insights.
PromptExp supports both white-box and black-box explanations and extends explanations to higher granularity levels.
We evaluate PromptExp in case studies such as sentiment analysis, showing the perturbation-based approach performs best.
arXiv Detail & Related papers (2024-10-16T22:25:15Z) - FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks.
We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
arXiv Detail & Related papers (2024-02-29T21:05:37Z) - Rethinking Interpretability in the Era of Large Language Models [76.1947554386879]
Large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks.
The capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human.
These new capabilities raise new challenges, such as hallucinated explanations and immense computational costs.
arXiv Detail & Related papers (2024-01-30T17:38:54Z) - LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
Recent large language models (LLM) are leveraging human feedback to improve their generation quality.
We propose LLMRefine, an inference time optimization method to refine LLM's output.
We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization.
LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
arXiv Detail & Related papers (2023-11-15T19:52:11Z) - Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method [36.24876571343749]
Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks.
Recent literature reveals that LLMs generate nonfactual responses intermittently.
We propose a novel self-detection method to detect which questions that a LLM does not know that are prone to generate nonfactual results.
arXiv Detail & Related papers (2023-10-27T06:22:14Z) - Survey on Factuality in Large Language Models: Knowledge, Retrieval and
Domain-Specificity [61.54815512469125]
This survey addresses the crucial issue of factuality in Large Language Models (LLMs)
As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
arXiv Detail & Related papers (2023-10-11T14:18:03Z) - Bad Actor, Good Advisor: Exploring the Role of Large Language Models in
Fake News Detection [22.658378054986624]
Large language models (LLMs) have shown remarkable performance in various tasks.
LLMs provide desirable multi-perspective rationales but still underperform the basic SLM, fine-tuned BERT.
We propose that current LLMs may not substitute fine-tuned SLMs in fake news detection but can be a good advisor for SLMs.
arXiv Detail & Related papers (2023-09-21T16:47:30Z)
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.