paper-with-me

홈 › Papers

Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning

2024-02-01 · Yao-Hung Hubert Tsai, Walter Talbott, Jian Zhang

Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models. Existing approaches are either white-box or computationally demanding, limiting use of black-box proprietary LLMs within budgets. The paper's first contribution is a non-parametric uncertainty quantification method for LLMs, efficiently estimating point-wise dependencies between input-decision on the fly with a single inference, without access to token logits. This estimator informs the statistical interpretation of decision trustworthiness. The second contribution outlines a systematic design for a decision-making agent, generating actions like `turn on the bathroom light'' based on user prompts such as `take a bath''. Users will be asked to provide preferences when more than one action has high estimated point-wise dependencies. In conclusion, our uncertainty estimation and decision-making agent design offer a cost-efficient approach for AI agent development.

📄 PDF Abstract BibTeX arXiv:2402.00251

Code (0)

등록된 구현이 없습니다.

Tasks

AI AgentDecision MakingHallucinationUncertainty Quantification

Similar Papers 제목 키워드 기반

Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation

2026-05-07 · Huizi Cui, Huan Ma, Qilin Wang, Yuhang Gao 외 arxiv

Large language models (LLMs) have progressed rapidly in complex reasoning and question answering, yet LLM hallucination remains a central bottleneck that hinders practical deployment, especially for commercial black-box …

Question Answering

Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models

2024-11-05 · Zizhang Chen, Peizhao Li, Xiaomeng Dong, Pengyu Hong

To facilitate healthcare delivery, language models (LMs) have significant potential for clinical prediction tasks using electronic health records (EHRs). However, in these high-stakes applications, unreliable decisions c…

PredictionUncertainty Quantification

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

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

2024-05-30 · Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen

Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve the trustworthiness of LLMs by detectin…

Text GenerationUncertainty Quantification

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models

2023-05-30 · Zhen Lin, Shubhendu Trivedi, Jimeng Sun

Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains. However, gauging the trustworthiness of responses genera…

ManagementQuestion AnsweringText GenerationUncertainty Quantification