paper-with-me

Papers

LUQ: Long-text Uncertainty Quantification for LLMs

2024-03-29 · Caiqi Zhang, Fangyu Liu, Marco Basaldella, Nigel Collier

Large Language Models (LLMs) have demonstrated remarkable capability in a variety of NLP tasks. However, LLMs are also prone to generate nonfactual content. Uncertainty Quantification (UQ) is pivotal in enhancing our understanding of a model's confidence on its generation, thereby aiding in the mitigation of nonfactual outputs. Existing research on UQ predominantly targets short text generation, typically yielding brief, word-limited responses. However, real-world applications frequently necessitate much longer responses. Our study first highlights the limitations of current UQ methods in handling long text generation. We then introduce \textsc{Luq} and its two variations, a series of novel sampling-based UQ approaches specifically designed for long text. Our findings reveal that \textsc{Luq} outperforms existing baseline methods in correlating with the model's factuality scores (negative coefficient of -0.85 observed for Gemini Pro). To further improve the factuality of LLM responses, we propose \textsc{Luq-Ensemble}, a method that ensembles responses from multiple models and selects the response with the lowest uncertainty. The ensembling method greatly improves the response factuality upon the best standalone LLM.

📄 PDF Abstract BibTeX arXiv:2403.20279

Code (1)

caiqizh/LUQ 공식 구현

Tasks

Text GenerationUncertainty Quantification

Similar Papers 제목 키워드 기반

IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation

2026-04-16 · Haozhi Fan, Jinhao Duan, Kaidi Xu arxiv

Despite the rapid advancement of Large Language Models (LLMs), uncertainty quantification in LLM generation is a persistent challenge. Although recent approaches have achieved strong performance by restricting LLMs to pr…

Text Generation

A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions

2024-12-07 · Ola Shorinwa, Zhiting Mei, Justin Lidard, Allen Z. Ren 외

The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises val…

ChatbotCommon Sense ReasoningUncertainty Quantificationvalid

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

2026-02-19 · Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj, David Skarbrevik arxiv

Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generalize well to long-form ge…

MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty

2024-08-13 · Yongjin Yang, Haneul Yoo, Hwaran Lee

Despite the massive advancements in large language models (LLMs), they still suffer from producing plausible but incorrect responses. To improve the reliability of LLMs, recent research has focused on uncertainty quantif…

Mathematical ReasoningQuestion AnsweringUncertainty QuantificationWorld Knowledge

AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation

2026-04-08 · Guanran Luo, Wentao Qiu, Wanru Zhao, Wenhan Lv 외 arxiv

Large Language Models (LLMs) have demonstrated impressive capabilities in long-form generation, yet their application is hindered by the hallucination problem. While Uncertainty Quantification (UQ) is essential for asses…

Text Generation