paper-with-me

Papers

Efficient semantic uncertainty quantification in language models via diversity-steered sampling

2025-10-24 · Ji Won Park, Kyunghyun Cho arxiv

Accurately estimating semantic aleatoric and epistemic uncertainties in large language models (LLMs) is particularly challenging in free-form question answering (QA), where obtaining stable estimates often requires many expensive generations. We introduce a diversity-steered sampler that discourages semantically redundant outputs during decoding, covers both autoregressive and masked diffusion paradigms, and yields substantial sample-efficiency gains. The key idea is to inject a continuous semantic-similarity penalty into the model's proposal distribution using a natural language inference (NLI) model lightly finetuned on partial prefixes or intermediate diffusion states. We debias downstream uncertainty estimates with importance reweighting and shrink their variance with control variates. Across four QA benchmarks, our method matches or surpasses baselines while covering more semantic clusters with the same number of samples. Being modular and requiring no gradient access to the base LLM, the framework promises to serve as a drop-in enhancement for uncertainty estimation in risk-sensitive model deployments.

📄 PDF Abstract BibTeX arXiv:2510.21310

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language InferenceQuestion Answering

Similar Papers 제목 키워드 기반

Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models

2025-06-11 · Haoyi Song, Ruihan Ji, Naichen Shi, Fan Lai 외

Large language models (LLMs) have transformed natural language processing, but their reliable deployment requires effective uncertainty quantification (UQ). Existing UQ methods are often heuristic and lack a probabilisti…

DiversitySemantic SimilaritySemantic Textual SimilarityUncertainty Quantification

Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

2026-02-27 · Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low arxiv

Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurate uncertainty metrics could enable escalation of unreliable queries …

Audio Generation

Semantic Self-Distillation for Language Model Uncertainty

2026-02-04 · Edward Phillips, Sean Wu, Fredrik K. Gustafsson, Boyan Gao 외 arxiv

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answe…

Answer Selection

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

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models

2025-10-15 · Mingda Li, Xinyu Li, Weinan Zhang, Longxuan Ma arxiv

Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work, we establish a connection between the un…

Computational Efficiency