GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation

• URL: http://arxiv.org/abs/2101.06561v1
• Date: Sun, 17 Jan 2021 00:40:47 GMT
• Title: GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation
• Authors: Daniel Khashabi, Gabriel Stanovsky, Jonathan Bragg, Nicholas Lourie, Jungo Kasai, Yejin Choi, Noah A. Smith, Daniel S. Weld
• Abstract summary: Leaderboards have eased model development for many NLP datasets by standardizing their evaluation and delegating it to an independent external repository. This work introduces GENIE, an human evaluation leaderboard, which brings the ease of leaderboards to text generation tasks.
• Score: 83.10599735938618
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Leaderboards have eased model development for many NLP datasets by standardizing their evaluation and delegating it to an independent external repository. Their adoption, however, is so far limited to tasks that can be reliably evaluated in an automatic manner. This work introduces GENIE, an extensible human evaluation leaderboard, which brings the ease of leaderboards to text generation tasks. GENIE automatically posts leaderboard submissions to crowdsourcing platforms asking human annotators to evaluate them on various axes (e.g., correctness, conciseness, fluency) and compares their answers to various automatic metrics. We introduce several datasets in English to GENIE, representing four core challenges in text generation: machine translation, summarization, commonsense reasoning, and machine comprehension. We provide formal granular evaluation metrics and identify areas for future research. We make GENIE publicly available and hope that it will spur progress in language generation models as well as their automatic and manual evaluation.

Related papers

• From Matching to Generation: A Survey on Generative Information Retrieval [21.56093567336119]
  generative information retrieval (GenIR) has emerged as a novel paradigm, gaining increasing attention in recent years. This paper aims to systematically review the latest research progress in GenIR.
  arXiv  Detail & Related papers  (2024-04-23T09:05:37Z)
• PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models [72.57329554067195]
  ProxyQA is an innovative framework dedicated to assessing longtext generation. It comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. It assesses the generated content's quality through the evaluator's accuracy in addressing the proxy-questions.
  arXiv  Detail & Related papers  (2024-01-26T18:12:25Z)
• Evaluation Metrics of Language Generation Models for Synthetic Traffic Generation Tasks [22.629816738693254]
  We show that common NLG metrics, like BLEU, are not suitable for evaluating Synthetic Traffic Generation (STG) We propose and evaluate several metrics designed to compare the generated traffic to the distribution of real user texts.
  arXiv  Detail & Related papers  (2023-11-21T11:26:26Z)
• VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use [49.574651930395305]
  VisIT-Bench is a benchmark for evaluation of instruction-following vision-language models. Our dataset comprises 592 test queries, each with a human-authored instruction-conditioned caption. We quantify quality gaps between models and references using both human and automatic evaluations.
  arXiv  Detail & Related papers  (2023-08-12T15:27:51Z)
• Large Language Models are Diverse Role-Players for Summarization Evaluation [82.31575622685902]
  A document summary's quality can be assessed by human annotators on various criteria, both objective ones like grammar and correctness, and subjective ones like informativeness, succinctness, and appeal. Most of the automatic evaluation methods like BLUE/ROUGE may be not able to adequately capture the above dimensions. We propose a new evaluation framework based on LLMs, which provides a comprehensive evaluation framework by comparing generated text and reference text from both objective and subjective aspects.
  arXiv  Detail & Related papers  (2023-03-27T10:40:59Z)
• An Overview on Controllable Text Generation via Variational Auto-Encoders [15.97186478109836]
  Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans. Latent variable models (LVM) such as variational auto-encoders (VAEs) are designed to characterize the distributional pattern of textual data. This overview gives an introduction to existing generation schemes, problems associated with text variational auto-encoders, and a review of several applications about the controllable generation.
  arXiv  Detail & Related papers  (2022-11-15T07:36:11Z)
• CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark [144.05723617401674]
  General-purpose language intelligence evaluation has been a longstanding goal for natural language processing. We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic. We propose CUGE, a Chinese Language Understanding and Generation Evaluation benchmark with the following features.
  arXiv  Detail & Related papers  (2021-12-27T11:08:58Z)
• Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand [117.62186420147563]
  We propose a generalization of leaderboards, bidimensional leaderboards (Billboards) Unlike conventional unidimensional leaderboards that sort submitted systems by predetermined metrics, a Billboard accepts both generators and evaluation metrics as competing entries. We demonstrate that a linear ensemble of a few diverse metrics sometimes substantially outperforms existing metrics in isolation.
  arXiv  Detail & Related papers  (2021-12-08T06:34:58Z)
• BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation [42.34923623457615]
  Bias in Open-Ended Language Generation dataset consists of 23,679 English text generation prompts. An examination of text generated from three popular language models reveals that the majority of these models exhibit a larger social bias than human-written Wikipedia text.
  arXiv  Detail & Related papers  (2021-01-27T22:07:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.