Can Large Language Models Detect Misinformation in Scientific News Reporting?

• URL: http://arxiv.org/abs/2402.14268v1
• Date: Thu, 22 Feb 2024 04:07:00 GMT
• Title: Can Large Language Models Detect Misinformation in Scientific News Reporting?
• Authors: Yupeng Cao, Aishwarya Muralidharan Nair, Elyon Eyimife, Nastaran Jamalipour Soofi, K.P. Subbalakshmi, John R. Wullert II, Chumki Basu, David Shallcross
• Abstract summary: This paper investigates whether it is possible to use large language models (LLMs) to detect misinformation in scientific reporting. We first present a new labeled dataset SciNews, containing 2.4k scientific news stories drawn from trusted and untrustworthy sources. We identify dimensions of scientific validity in science news articles and explore how this can be integrated into the automated detection of scientific misinformation.
• Score: 1.0344642971058586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific facts are often spun in the popular press with the intent to influence public opinion and action, as was evidenced during the COVID-19 pandemic. Automatic detection of misinformation in the scientific domain is challenging because of the distinct styles of writing in these two media types and is still in its nascence. Most research on the validity of scientific reporting treats this problem as a claim verification challenge. In doing so, significant expert human effort is required to generate appropriate claims. Our solution bypasses this step and addresses a more real-world scenario where such explicit, labeled claims may not be available. The central research question of this paper is whether it is possible to use large language models (LLMs) to detect misinformation in scientific reporting. To this end, we first present a new labeled dataset SciNews, containing 2.4k scientific news stories drawn from trusted and untrustworthy sources, paired with related abstracts from the CORD-19 database. Our dataset includes both human-written and LLM-generated news articles, making it more comprehensive in terms of capturing the growing trend of using LLMs to generate popular press articles. Then, we identify dimensions of scientific validity in science news articles and explore how this can be integrated into the automated detection of scientific misinformation. We propose several baseline architectures using LLMs to automatically detect false representations of scientific findings in the popular press. For each of these architectures, we use several prompt engineering strategies including zero-shot, few-shot, and chain-of-thought prompting. We also test these architectures and prompting strategies on GPT-3.5, GPT-4, and Llama2-7B, Llama2-13B.

Related papers

• Scientific QA System with Verifiable Answers [0.0]
  We introduce the VerifAI project, a pioneering open-source scientific question-answering system. The components of the system are (1) an Information Retrieval system combining semantic and lexical search techniques over scientific papers (Mistral 7B) and retrieved articles to generate claims with references to the articles from which it was derived, (2) a Retrieval-Augmented Generation (RAG) module using fine-tuned generative model (Mistral 7B) and retrieved articles to generate claims with references to the articles from which it was derived, and (3) a Verification engine, based on a fine-tuned DeBERTa
  arXiv  Detail & Related papers  (2024-07-16T08:21:02Z)
• SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions [52.35520385083425]
  We present SciDMT, an enhanced and expanded corpus for scientific mention detection. The corpus consists of two components: 1) the SciDMT main corpus, which includes 48 thousand scientific articles with over 1.8 million weakly annotated mention annotations in the format of in-text span, and 2) an evaluation set, which comprises 100 scientific articles manually annotated for evaluation purposes.
  arXiv  Detail & Related papers  (2024-06-20T22:03:21Z)
• A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery [68.48094108571432]
  Large language models (LLMs) have revolutionized the way text and other modalities of data are handled. We aim to provide a more holistic view of the research landscape by unveiling cross-field and cross-modal connections between scientific LLMs.
  arXiv  Detail & Related papers  (2024-06-16T08:03:24Z)
• Mapping the Increasing Use of LLMs in Scientific Papers [99.67983375899719]
  We conduct the first systematic, large-scale analysis across 950,965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals. Our findings reveal a steady increase in LLM usage, with the largest and fastest growth observed in Computer Science papers.
  arXiv  Detail & Related papers  (2024-04-01T17:45:15Z)
• Modeling Information Change in Science Communication with Semantically Matched Paraphrases [50.67030449927206]
  SPICED is the first paraphrase dataset of scientific findings annotated for degree of information change. SPICED contains 6,000 scientific finding pairs extracted from news stories, social media discussions, and full texts of original papers. Models trained on SPICED improve downstream performance on evidence retrieval for fact checking of real-world scientific claims.
  arXiv  Detail & Related papers  (2022-10-24T07:44:38Z)
• SciLander: Mapping the Scientific News Landscape [8.504643390943409]
  We introduce SciLander, a method for learning representations of news sources reporting on science-based topics. We evaluate our method on a novel COVID-19 dataset containing nearly 1M news articles from 500 sources spanning a period of 18 months since the beginning of the pandemic in 2020.
  arXiv  Detail & Related papers  (2022-05-16T20:20:43Z)
• SciEv: Finding Scientific Evidence Papers for Scientific News [5.6164173936437045]
  We propose a system called SciEv that searches for scientific evidence papers given a scientific news article. The key feature of SciEv is it uses domain knowledge entities (DKEs) to find candidates in the first stage. To evaluate our system, we compiled a pilot dataset consisting of 100 manually curated (news, paper) pairs from ScienceAlert and similar websites.
  arXiv  Detail & Related papers  (2022-04-30T01:43:23Z)
• Semi-Supervised Exaggeration Detection of Health Science Press Releases [23.930041685595775]
  Recent studies have demonstrated a tendency of news media to misrepresent scientific papers by exaggerating their findings. We present a formalization of and study into the problem of exaggeration detection in science communication. We introduce MT-PET, a multi-task version of Pattern Exploiting Training (PET), which leverages knowledge from complementary cloze-style QA tasks to improve few-shot learning.
  arXiv  Detail & Related papers  (2021-08-30T19:32:20Z)
• Misinformation Has High Perplexity [55.47422012881148]
  We propose to leverage the perplexity to debunk false claims in an unsupervised manner. First, we extract reliable evidence from scientific and news sources according to sentence similarity to the claims. Second, we prime a language model with the extracted evidence and finally evaluate the correctness of given claims based on the perplexity scores at debunking time.
  arXiv  Detail & Related papers  (2020-06-08T15:13:44Z)
• Fact or Fiction: Verifying Scientific Claims [53.29101835904273]
  We introduce scientific claim verification, a new task to select abstracts from the research literature containing evidence that SUPPORTS or REFUTES a given scientific claim. We construct SciFact, a dataset of 1.4K expert-written scientific claims paired with evidence-containing abstracts annotated with labels and rationales. We show that our system is able to verify claims related to COVID-19 by identifying evidence from the CORD-19 corpus.
  arXiv  Detail & Related papers  (2020-04-30T17:22:57Z)

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.