arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.03300cs.CLcs.AI
收藏

VERITAS:一种统一的可靠性评估方法

VERITAS: A Unified Approach to Reliability Evaluation

Collinear AI(科林尼尔人工智能公司)

Rajkumar Ramamurthy, Meghana Arakkal Rajeev, Oliver Molenschot, James Zou, Nazneen Rajani

AI总结:

VERITAS提出统一的幻觉检测模型系列,跨上下文灵活评估可靠性,平均性能提升10%,接近GPT-4 Turbo。

摘要:

大型语言模型(LLMs)常常无法综合其上下文中的信息来生成准确的响应。这使得它们在知识密集型环境中变得不可靠,而输出的可靠性是关键。可靠LLM的一个关键组成部分是集成一个强大的事实核查系统,该系统能够检测各种格式的幻觉。虽然有几个开放获取的事实核查模型可用,但其功能通常局限于特定任务,如基于地面的问答或蕴含验证,并且在对话场景中表现较差。另一方面,像GPT-4和Claude这样的封闭访问模型在不同上下文中提供了更大的灵活性,包括基于对话的验证,但受到高成本和延迟的阻碍。在这项工作中,我们引入了VERITAS,一个幻觉检测模型系列,旨在跨不同上下文灵活操作,同时最小化延迟和成本。VERITAS在考虑所有主要幻觉检测基准的平均性能时取得了最先进的结果,与类似规模的模型相比,平均性能提高了10%,并且在LLM-as-a-judge设置下接近GPT-4 Turbo的性能。

英文摘要:

Large language models (LLMs) often fail to synthesize information from their context to generate an accurate response. This renders them unreliable in knowledge intensive settings where reliability of the output is key. A critical component for reliable LLMs is the integration of a robust fact-checking system that can detect hallucinations across various formats. While several open-access fact-checking models are available, their functionality is often limited to specific tasks, such as grounded question-answering or entailment verification, and they perform less effectively in conversational settings. On the other hand, closed-access models like GPT-4 and Claude offer greater flexibility across different contexts, including grounded dialogue verification, but are hindered by high costs and latency. In this work, we introduce VERITAS, a family of hallucination detection models designed to operate flexibly across diverse contexts while minimizing latency and costs. VERITAS achieves state-of-the-art results considering average performance on all major hallucination detection benchmarks, with $10\%$ increase in average performance when compared to similar-sized models and get close to the performance of GPT4 turbo with LLM-as-a-judge setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑