Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers

2023-10-16 · Charlie George, Andreas Stuhlmüller

Hallucination plagues even frontier LLMs--but how bad is it really for summarizing academic papers? We evaluate Factored Verification, a simple automated method for detecting hallucinations in abstractive summaries. This method sets a new SotA on hallucination detection in the summarization task of the HaluEval benchmark, achieving 76.2% accuracy. We then use this method to estimate how often language models hallucinate when summarizing across multiple academic papers and find 0.62 hallucinations in the average ChatGPT (16k) summary, 0.84 for GPT-4, and 1.55 for Claude 2. We ask models to self-correct using Factored Critiques and find that this lowers the number of hallucinations to 0.49 for ChatGPT, 0.46 for GPT-4, and 0.95 for Claude 2. The hallucinations we find are often subtle, so we advise caution when using models to synthesize academic papers.

📄 PDF Abstract BibTeX arXiv:2310.10627

Code (1)

elicit/fave-dataset 공식 구현

Tasks

16kHallucination

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Residual Connection 설명 없음

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Multi-Head Attention 설명 없음

Reducing Quantity Hallucinations in Abstractive Summarization

2020-09-28 · Findings of the Association for Computational Linguistics 2020 · Zheng Zhao, Shay B. Cohen, Bonnie Webber

It is well-known that abstractive summaries are subject to hallucination---including material that is not supported by the original text. While summaries can be made hallucination-free by limiting them to general phrases…

Abstractive Text Summarization Hallucination

Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations

2024-05-07 · Hassan Shakil, Zeydy Ortiz, Grant C. Forbes

In this research, we uses the DistilBERT model to generate extractive summary and the T5 model to generate abstractive summaries. Also, we generate hybrid summaries by combining both DistilBERT and T5 models. Central to …

Text Summarization

ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset

2025-01-16 · Fen Wang, Bomiao Wang, Xueli Shu, Zhen Liu 외

Effective chart summary can significantly reduce the time and effort decision makers spend interpreting charts, enabling precise and efficient communication of data insights. Previous studies have faced challenges in gen…

Hallucination Sentence Time Series

ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries

2024-10-17 · Kishan Maharaj, Vitobha Munigala, Srikanth G. Tamilselvam, Prince Kumar 외

Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in tasks like natural language-to-code (NL2Code) and code summ…

Code Summarization Hallucination

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention

2026-02-20 · Siya Qi, Yudong Chen, Runcong Zhao, Qinglin Zhu 외 arxiv

Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available during generation, among which attention o…