paper-with-me

홈 › Papers

Accurate and Nuanced Open-QA Evaluation Through Textual Entailment

2024-05-26 · Peiran Yao, Denilson Barbosa

Open-domain question answering (Open-QA) is a common task for evaluating large language models (LLMs). However, current Open-QA evaluations are criticized for the ambiguity in questions and the lack of semantic understanding in evaluators. Complex evaluators, powered by foundation models or LLMs and pertaining to semantic equivalence, still deviate from human judgments by a large margin. We propose to study the entailment relations of answers to identify more informative and more general system answers, offering a much closer evaluation to human judgment on both NaturalQuestions and TriviaQA while being learning-free. The entailment-based evaluation we propose allows the assignment of bonus or partial marks by quantifying the inference gap between answers, enabling a nuanced ranking of answer correctness that has higher AUC than current methods.

📄 PDF Abstract BibTeX arXiv:2405.16702

Code (1)

U-Alberta/QA-partial-marks 공식 구현 pytorch

Tasks

Natural Language InferenceOpen-Domain Question AnsweringQuestion AnsweringTriviaQA

Similar Papers 제목 키워드 기반

IndiCASA: A Dataset and Bias Evaluation Framework in LLMs Using Contrastive Embedding Similarity in the Indian Context

2025-10-03 · Santhosh G S, Akshay Govind S, Gokul S Krishnan, Balaraman Ravindran 외 arxiv

Large Language Models (LLMs) have gained significant traction across critical domains owing to their impressive contextual understanding and generative capabilities. However, their increasing deployment in high stakes ap…

Contrastive Learning

AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models

2025-09-19 · Vatsal Malaviya, Agneet Chatterjee, Maitreya Patel, Yezhou Yang 외 arxiv

Text-to-Image (T2I) models have recently achieved remarkable success in generating images from textual descriptions. However, challenges still persist in accurately rendering complex scenes where actions and interactions…

Knowledge DistillationImage Generation

ERASMO: Leveraging Large Language Models for Enhanced Clustering Segmentation

2024-10-01 · Fillipe dos Santos Silva, Gabriel Kenzo Kakimoto, Julio Cesar Dos Reis, Marcelo S. Reis

Cluster analysis plays a crucial role in various domains and applications, such as customer segmentation in marketing. These contexts often involve multimodal data, including both tabular and textual datasets, making it …

ClusteringLanguage ModelingLanguage ModellingMarketing

Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings

2025-09-29 · Hamna Hamna, Gayatri Bhat, Sourabrata Mukherjee, Faisal Lalani 외 arxiv

Large Language Models (LLMs) are typically evaluated through general or domain-specific benchmarks testing capabilities that often lack grounding in the lived realities of end users. Critical domains such as healthcare r…

TMCIR: Token Merge Benefits Composed Image Retrieval

2025-04-15 · Chaoyang Wang, Zeyu Zhang, Long Teng, Zijun Li 외

Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and tex…

Contrastive Learningcross-modal alignmentImage RetrievalImage to text+1