paper-with-me

Papers

FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation

2024-10-29 · Farima Fatahi Bayat, Lechen Zhang, Sheza Munir, Lu Wang

The rapid adoption of language models (LMs) across diverse applications has raised concerns about their factuality, i.e., their consistency with real-world facts. We first present VERIFY (Verification and Evidence RetrIeval for FactualitY evaluation), a pipeline to evaluate LMs' factuality in real-world user interactions. VERIFY considers the verifiability of LM-generated content and categorizes content units as supported, unsupported, or undecidable based on Web-retrieved evidence. Importantly, factuality judgment by VERIFY correlates better with human evaluations than existing methods. Using VERIFY, we identify "hallucination prompts" across diverse topics, i.e., those eliciting the highest rates of incorrect (unsupported) and inconclusive (undecidable) LM responses. These prompts form FACTBENCH, a dataset of 1K prompts across 150 fine-grained topics. Our dataset captures emerging factuality challenges in real-world LM interactions and can be regularly updated with new prompts. We benchmark widely-used LMs from GPT, Gemini, and Llama families on FACTBENCH, yielding the following key findings: (i) Proprietary models exhibit better factuality, with decreased performance from Easy to Hard hallucination prompts. (ii) Llama3.1-405B-Instruct shows comparable or lower factual precision than Llama3.1-70B-Instruct across all evaluation methods due to its higher subjectivity that leads to more content labeled as undecidable. (iii) Gemini1.5-Pro shows a significantly higher refusal rate, with over-refusal in 25% of cases.

📄 PDF Abstract BibTeX arXiv:2410.22257

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Multi-Head 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 $x$…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain

2025-09-02 · Anum Afzal, Juraj Vladika, Florian Matthes arxiv

Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources…

Natural Language Inference

RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking

2025-06-14 · Shuo Yang, Yuqin Dai, Guoqing Wang, Xinran Zheng 외

Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comp…

Explanation GenerationFact CheckingMisinformation

UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking

2025-05-21 · Sarfraz Ahmad, Hasan Iqbal, Momina Ahsan, Numaan Naeem 외

The rapid use of large language models (LLMs) has raised critical concerns regarding the factual reliability of their outputs, especially in low-resource languages such as Urdu. Existing automated fact-checking solutions…

BenchmarkingClaim VerificationFact CheckingQuestion Answering+1

Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration

2026-04-13 · Xin Liu, Lu Wang arxiv

Large language models (LLMs) often hallucinate in long-form generation. Existing approaches mainly improve factuality through post-hoc revision or reinforcement learning (RL) with correctness-based rewards, but they do n…

Reinforcement Learning

WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries

2024-07-24 · Wenting Zhao, Tanya Goyal, Yu Ying Chiu, Liwei Jiang 외

While hallucinations of large language models (LLMs) prevail as a major challenge, existing evaluation benchmarks on factuality do not cover the diverse domains of knowledge that the real-world users of LLMs seek informa…

ChatbotFormHallucinationRetrieval