paper-with-me

홈 › Papers

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

2024-02-20 · Liyan Tang, Igor Shalyminov, Amy Wing-mei Wong, Jon Burnsky, Jake W. Vincent, Yu'an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su, Lijia Sun, Yi Zhang, Saab Mansour, Kathleen McKeown

Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text summarization domains. We propose a new evaluation benchmark on topic-focused dialogue summarization, generated by LLMs of varying sizes. We provide binary sentence-level human annotations of the factual consistency of these summaries along with detailed explanations of factually inconsistent sentences. Our analysis shows that existing LLMs hallucinate significant amounts of factual errors in the dialogue domain, regardless of the model's size. On the other hand, when LLMs, including GPT-4, serve as binary factual evaluators, they perform poorly and can be outperformed by prevailing state-of-the-art specialized factuality evaluation metrics. Finally, we conducted an analysis of hallucination types with a curated error taxonomy. We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.

📄 PDF Abstract BibTeX arXiv:2402.13249

Code (1)

amazon-science/tofueval 공식 구현

Tasks

HallucinationNews SummarizationSentenceText Summarization

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
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 $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization

2024-10-17 · Catarina G. Belem, Pouya Pezeskhpour, Hayate Iso, Seiji Maekawa 외

Although many studies have investigated and reduced hallucinations in large language models (LLMs) for single-document tasks, research on hallucination in multi-document summarization (MDS) tasks remains largely unexplor…

Document SummarizationHallucinationMulti-Document Summarization

HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models

2023-05-19 · Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie 외

Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to…

HallucinationHallucination Evaluation

Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization

2025-03-03 · Siya Qi, Rui Cao, Yulan He, Zheng Yuan

With the rapid development of large language models (LLMs), LLM-as-a-judge has emerged as a widely adopted approach for text quality evaluation, including hallucination evaluation. While previous studies have focused exc…

HallucinationHallucination Evaluation

Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective

2024-11-21 · Ernests Lavrinovics, Russa Biswas, Johannes Bjerva, Katja Hose

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) based applications including automated text generation, question answering, chatbots, and others. However, they face a significant challe…

Knowledge GraphsQuestion AnsweringText Generation

CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence

2024-06-11 · Md Tanvirul Alam, Dipkamal Bhusal, Le Nguyen, Nidhi Rastogi

Cyber threat intelligence (CTI) is crucial in today's cybersecurity landscape, providing essential insights to understand and mitigate the ever-evolving cyber threats. The recent rise of Large Language Models (LLMs) have…