Authors:
(1) Jerry Wei, Google DeepMind and a Lead contributors;
(2) Chengrun Yang, Google DeepMind and a Lead contributors;
(3) Xinying Song, Google DeepMind and a Lead contributors;
(4) Yifeng Lu, Google DeepMind and a Lead contributors;
(5) Nathan Hu, Google DeepMind and Stanford University;
(6) Jie Huang, Google DeepMind and University of Illinois at Urbana-Champaign;
(7) Dustin Tran, Google DeepMind;
(8) Daiyi Peng, Google DeepMind;
(9) Ruibo Liu, Google DeepMind;
(10) Da Huang, Google DeepMind;
(11) Cosmo Du, Google DeepMind;
(12) Quoc V. Le, Google DeepMind. Authors: Authors: (1) Jerry Wei, Google DeepMind and a Lead contributors; (2) Chengrun Yang, Google DeepMind and a Lead contributors; (3) Xinying Song, Google DeepMind and a Lead contributors; (4) Yifeng Lu, Google DeepMind and a Lead contributors; (5) Nathan Hu, Google DeepMind and Stanford University; (6) Jie Huang, Google DeepMind and University of Illinois at Urbana-Champaign; (7) Dustin Tran, Google DeepMind; (8) Daiyi Peng, Google DeepMind; (9) Ruibo Liu, Google DeepMind; (10) Da Huang, Google DeepMind; (11) Cosmo Du, Google DeepMind; (12) Quoc V. Le, Google DeepMind. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 LongFact: Using LLMs to generate a multi-topic benchmark for long-form factuality 2 LongFact: Using LLMs to generate a multi-topic benchmark for long-form factuality 3 Safe:LLM agents as factuality autoraters 3 Safe:LLM agents as factuality autoraters 4 LLMs agents can be better factuality annotators than humans 4 LLMs agents can be better factuality annotators than humans 5 F1@k: Extending F1 with recall from human-preferred length 5 F1@k: Extending F1 with recall from human-preferred length 6 Larger LLMs are more factual 6 Larger LLMs are more factual 7 Related Work 7 Related Work 8 Limitations 8 Limitations 9 Conclusion, Acknowledgments, Author Contribution, and References 9 Conclusion, Acknowledgments, Author Contribution, and References Appendix Appendix A. Frequently asked questions A. Frequently asked questions B. LongFact details B. LongFact details C. SAFE details C. SAFE details D. Metric details D. Metric details E. Further analysis E. Further analysis ABSTRACT Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model’s long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for longform factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user’s preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators—on a set of ∼16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https://github. com/google-deepmind/long-form-factuality. 1 INTRODUCTION Large Language Models (LLMs) have significantly improved in recent years (Brown et al., 2020; Chowdhery et al., 2022; Google, 2023; OpenAI, 2023; Gemini Team, 2023, inter alia) but still lack reliability in responding to in-depth factuality questions. In particular, they often produce factual errors in which a claim contradicts established ground-truth knowledge (Huang et al., 2023; Zhang et al., 2023, inter-alia).[1] For example, models may respond with incorrect information about established facts such as dates, statistics, or even a celebrity’s occupation (Li et al., 2023; Min et al., 2023; Muhlgay et al., 2023). These factual errors weaken a language model’s factuality, making the model unreliable in many real-world settings where a factually-accurate response is expected. In this paper, we propose a new prompt set called LongFact, an evaluation method named SAFE, and a metric (F1@K) for quantifying the long-form factuality of a long-form response. We then extensively benchmark popular large language models using these new datasets and evaluation methods. Our contributions are as follows: • We use GPT-4[2] to generate a new prompt set for benchmarking long-form factuality in large language models, which we call LongFact (Section 2). LongFact consists of 2,280 fact-seeking prompts that solicit long-form responses across 38 manually-selected topics. To our knowledge, LongFact is the first prompt set for evaluating long-form factuality in a wide variety of domains. We make LongFact publicly available at https://github.com/google-deepmind/ long-form-factuality/tree/main/longfact. • We propose a method of utilizing an LLM agent to automatically evaluate long-form factuality in model responses. We use the language model to first decompose a long-form response into individual facts, then for each fact, propose fact-checking queries to send to a Google Search API and reason about whether the fact is supported by search results (Section 3). We name this method SAFE (Search-Augmented Factuality Evaluator).[3] Empirically, SAFE outperforms crowdsourced human annotators, agreeing with 72% of human annotations from Min et al. (2023) and winning 76% of disagreement cases from a random sample of 100 disagreement cases (Section 4). SAFE is also 20× cheaper than human annotators. We release SAFE at https://github.com/ google-deepmind/long-form-factuality/tree/main/eval/safe. • We propose that when quantifying the long-form factuality of a model response, F1 can be utilized via a hyperparameter that estimates the human-preferred “ideal” number of facts in a response. We therefore introduce F1@K, which (in addition to measuring a response’s factual precision as the ratio of supported facts) measures recall as the ratio of provided supported facts over a variable desired number of supported facts K. • We conduct an extensive benchmark of thirteen large language models across four model families (Gemini, GPT, Claude, and PaLM-2) on LongFact (Section 6). We evaluate model responses using SAFE and quantify performance using F1@K, finding that, in general, larger language models achieve better long-form factuality. This paper is available on arxiv under CC by 4.0 Deed license. This paper is available on arxiv under CC by 4.0 Deed license. available on arxiv available on arxiv [1] We focus on factuality and factual errors, not hallucination, as our proposed evaluation method focuses on determining whether a response is factual with respect to external established knowledge (factuality) rather than whether the response is consistent with the model’s internal knowledge (hallucination). [2] We use gpt-4-0613 for GPT-4. [3] In our implementation of SAFE, we use gpt-3.5-turbo-0125 as the language model and Serper (available at https://serper.dev/) as the Google Search API.

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

The AI Truth Test: New Study Tests the Accuracy of 13 Major AI Models

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

TnT-LLM Implementation Details: Pipeline Design, Robustness, and Efficiency

Prebunking Design as a Defense Mechanism Against Misinformation Propagation on Social Networks

Effective Methods for Combating Fake News: Censorship, Debunking, and Prebunking

Modeling Misinformation Propagation on Social Media

Enhancing User Protection with Optimal Prebunking in Social Networks

TnT-LLM Implementation Details: Pipeline Design, Robustness, and Efficiency

Prebunking Design as a Defense Mechanism Against Misinformation Propagation on Social Networks

Effective Methods for Combating Fake News: Censorship, Debunking, and Prebunking

Modeling Misinformation Propagation on Social Media

Enhancing User Protection with Optimal Prebunking in Social Networks

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps