paper-with-me

Papers

Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks

2024-08-07 · Zizhang Chen, Pengyu Hong, Sandeep Madireddy

Uncertainty quantification enables users to assess the reliability of responses generated by large language models (LLMs). We present a novel Question Rephrasing technique to evaluate the input uncertainty of LLMs, which refers to the uncertainty arising from equivalent variations of the inputs provided to LLMs. This technique is integrated with sampling methods that measure the output uncertainty of LLMs, thereby offering a more comprehensive uncertainty assessment. We validated our approach on property prediction and reaction prediction for molecular chemistry tasks.

📄 PDF Abstract BibTeX arXiv:2408.03732

Code (0)

등록된 구현이 없습니다.

Tasks

PredictionProperty PredictionUncertainty Quantification

Similar Papers 제목 키워드 기반

Quantifying the Risks of Tool-assisted Rephrasing to Linguistic Diversity

2024-10-23 · Mengying Wang, Andreas Spitz

Writing assistants and large language models see widespread use in the creation of text content. While their effectiveness for individual users has been evaluated in the literature, little is known about their proclivity…

Diversity

Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries

2024-05-22 · Adam Yang, Chen Chen, Konstantinos Pitas

State-of-the-art large language models are sometimes distributed as open-source software but are also increasingly provided as a closed-source service. These closed-source large-language models typically see the widest u…

Can Pre-training help VQA with Lexical Variations?

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Shailza Jolly, Shubham Kapoor

Rephrasings or paraphrases are sentences with similar meanings expressed in different ways. Visual Question Answering (VQA) models are closing the gap with the oracle performance for datasets like VQA2.0. However, these …

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models

2026-01-30 · Khiem Le, Phuc Nguyen, Youssef Mroueh, Chi-Heng Lin 외 arxiv

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and d…

Reinforcement Learning

Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA

2022-11-14 · Elias Stengel-Eskin, Jimena Guallar-Blasco, Yi Zhou, Benjamin Van Durme

Natural language is ambiguous. Resolving ambiguous questions is key to successfully answering them. Focusing on questions about images, we create a dataset of ambiguous examples. We annotate these, grouping answers by th…

Question GenerationQuestion-GenerationVisual Question Answering (VQA)