Papers with uncertainty measure

4 papers
Uncertainty Propagation on LLM Agent (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for estimating uncertainty in large language models (LLMs) focus on final-step outputs, which fail to account for cumulative uncertainty over multi-step decision-making process and dynamic interactions between agents and their environments.
Approach: They propose a framework that propagates uncertainty through each step of an LLM-based agent’s reasoning process.
Outcome: Extensive experiments on benchmark datasets show that the proposed framework outperforms state-of-the-art methods by 20%.
Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue (2022.findings-acl)

Copied to clipboard

Challenge: Xu et al., 2019; Lewis e t al, 2019) show that Bayesian summarization methods can generate high quality summaries but suffer from a couple of issues when inputs lie far from the training data distribution.
Approach: They propose to extend state-of-the-art summarization models with Monte Carlo dropout and perform multiple stochastic forward passes to approximate Bayesian inference.
Outcome: The proposed method outperforms deterministic summarization models on multiple benchmark datasets.
ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)

Copied to clipboard

Challenge: Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs.
Approach: They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets.
Outcome: Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks.
Towards Statistical Factuality Guarantee for Large Vision-Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive performance in image-conditioned text generation, but hallucinated outputs pose a major barrier to their use in safety-critical applications.
Approach: They propose a conformal-prediction-based framework that achieves finite-sample distribution-free statistical guarantees to the factuality of LVLM output.
Outcome: The proposed framework reduces the error rate of LLaVa-1.5 claims from 87.8% to 10.0% while ensuring that the output is accurate.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations