Language Model Evaluation in Open-ended Text Generation
- URL: http://arxiv.org/abs/2108.03578v1
- Date: Sun, 8 Aug 2021 06:16:02 GMT
- Title: Language Model Evaluation in Open-ended Text Generation
- Authors: An Nguyen
- Abstract summary: We study different evaluation metrics that have been proposed to evaluate quality, diversity and consistency of machine-generated text.
From there, we propose a practical pipeline to evaluate language models in open-ended generation task.
- Score: 0.76146285961466
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Although current state-of-the-art language models have achieved impressive
results in numerous natural language processing tasks, still they could not
solve the problem of producing repetitive, dull and sometimes inconsistent text
in open-ended text generation. Studies often attribute this problem to the
maximum likelihood training objective, and propose alternative approaches by
using stochastic decoding methods or altering the training objective. However,
there is still a lack of consistent evaluation metrics to directly compare the
efficacy of these solutions. In this work, we study different evaluation
metrics that have been proposed to evaluate quality, diversity and consistency
of machine-generated text. From there, we propose a practical pipeline to
evaluate language models in open-ended generation task, and research on how to
improve the model's performance in all dimensions by leveraging different
auxiliary training objectives.
Related papers
- Likelihood as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
We show that likelihoods serve as an effective gauge for language model performance.
We propose two methods that use question likelihood as a gauge for selecting and constructing prompts that lead to better performance.
arXiv Detail & Related papers (2024-11-12T13:14:09Z) - Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework [0.1979158763744267]
Open-ended text generation has become a prominent task in natural language processing.
Decoding methods often excel in some metrics while underperforming in others.
We present novel ranking strategies within this multicriteria framework.
arXiv Detail & Related papers (2024-10-24T11:32:01Z) - Who Writes the Review, Human or AI? [0.36498648388765503]
This study proposes a methodology to accurately distinguish AI-generated and human-written book reviews.
Our approach utilizes transfer learning, enabling the model to identify generated text across different topics.
The experimental results demonstrate that it is feasible to detect the original source of text, achieving an accuracy rate of 96.86%.
arXiv Detail & Related papers (2024-05-30T17:38:44Z) - Lessons from the Trenches on Reproducible Evaluation of Language Models [60.522749986793094]
We draw on three years of experience in evaluating large language models to provide guidance and lessons for researchers.
We present the Language Model Evaluation Harness (lm-eval), an open source library for independent, reproducible, and evaluation of language models.
arXiv Detail & Related papers (2024-05-23T16:50:49Z) - Exploring Precision and Recall to assess the quality and diversity of LLMs [82.21278402856079]
We introduce a novel evaluation framework for Large Language Models (LLMs) such as textscLlama-2 and textscMistral.
This approach allows for a nuanced assessment of the quality and diversity of generated text without the need for aligned corpora.
arXiv Detail & Related papers (2024-02-16T13:53:26Z) - Beyond Turing: A Comparative Analysis of Approaches for Detecting Machine-Generated Text [1.919654267936118]
Traditional shallow learning, Language Model (LM) fine-tuning, and Multilingual Model fine-tuning are evaluated.
Results reveal considerable differences in performance across methods.
This study paves the way for future research aimed at creating robust and highly discriminative models.
arXiv Detail & Related papers (2023-11-21T06:23:38Z) - Language Model Decoding as Direct Metrics Optimization [87.68281625776282]
Current decoding methods struggle to generate texts that align with human texts across different aspects.
In this work, we frame decoding from a language model as an optimization problem with the goal of strictly matching the expected performance with human texts.
We prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts.
arXiv Detail & Related papers (2023-10-02T09:35:27Z) - A Contrastive Framework for Neural Text Generation [46.845997620234265]
We show that an underlying reason for model degeneration is the anisotropic distribution of token representations.
We present a contrastive solution: (i) SimCTG, a contrastive training objective to calibrate the model's representation space, and (ii) a decoding method -- contrastive search -- to encourage diversity while maintaining coherence in the generated text.
arXiv Detail & Related papers (2022-02-13T21:46:14Z) - Analyzing the Limits of Self-Supervision in Handling Bias in Language [52.26068057260399]
We evaluate how well language models capture the semantics of four tasks for bias: diagnosis, identification, extraction and rephrasing.
Our analyses indicate that language models are capable of performing these tasks to widely varying degrees across different bias dimensions, such as gender and political affiliation.
arXiv Detail & Related papers (2021-12-16T05:36:08Z) - TextFlint: Unified Multilingual Robustness Evaluation Toolkit for
Natural Language Processing [73.16475763422446]
We propose a multilingual robustness evaluation platform for NLP tasks (TextFlint)
It incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis.
TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness.
arXiv Detail & Related papers (2021-03-21T17:20:38Z)
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.