paper-with-me

홈 › Papers

Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework

2024-10-24 · Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Meimingwei Li, Christian Heumann, Matthias Aßenmacher

Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains challenging because of trade-offs among widely used metrics such as coherence, diversity, and perplexity. Decoding methods often excel in some metrics while underperforming in others, complicating the establishment of a clear ranking. In this paper, we present novel ranking strategies within this multicriteria framework. Specifically, we employ benchmarking approaches based on partial orderings and present a new summary metric designed to balance existing automatic indicators, providing a more holistic evaluation of text generation quality. Furthermore, we discuss the alignment of these approaches with human judgments. Our experiments demonstrate that the proposed methods offer a robust way to compare decoding strategies, exhibit similarities with human preferences, and serve as valuable tools in guiding model selection for open-ended text generation tasks. Finally, we suggest future directions for improving evaluation methodologies in text generation. Our codebase, datasets, and models are publicly available.

📄 PDF Abstract BibTeX arXiv:2410.18653

Code (1)

YecanLee/2BeOETG 공식 구현 pytorch

Tasks

BenchmarkingDiversityModel SelectionText Generation

Similar Papers 제목 키워드 기반

An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation

2022-11-19 · Yixuan Su, Jialu Xu

In the study, we empirically compare the two recently proposed decoding methods, i.e. Contrastive Search (CS) and Contrastive Decoding (CD), for open-ended text generation. The automatic evaluation results suggest that, …

DiversityText Generation

Interpretable neural networks based on continuous-valued logic and multicriteria decision operators

2019-10-06 · Orsolya Csiszár, Gábor Csiszár, József Dombi

Combining neural networks with continuous logic and multicriteria decision making tools can reduce the black box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathema…

Decision Making

A Hypervolume Based Approach to Rank Intuitionistic Fuzzy Sets and Its Extension to Multi-criteria Decision Making Under Uncertainty

2022-12-25 · Kaan Deveci, Onder Guler

Ranking intuitionistic fuzzy sets with distance based ranking methods requires to calculate the distance between intuitionistic fuzzy set and a reference point which is known to have either maximum (positive ideal soluti…

Decision MakingDecision Making Under Uncertaintyvalid

The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation

2021-09-14 · EMNLP 2021 11 · Marzena Karpinska, Nader Akoury, Mohit Iyyer

Recent text generation research has increasingly focused on open-ended domains such as story and poetry generation. Because models built for such tasks are difficult to evaluate automatically, most researchers in the spa…

Text Generation

Comparative Statics in Multicriteria Search Models

2020-06-25

McCall (1970) examines the search behaviour of an infinitely-lived and risk-neutral job seeker maximizing her lifetime earnings by accepting or rejecting real-valued scalar wage offers. In practice, job offers have multi…