How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments

• URL: http://arxiv.org/abs/2408.09639v1
• Date: Mon, 19 Aug 2024 01:53:47 GMT
• Title: How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments
• Authors: Yusuke Ide, Yuto Nishida, Miyu Oba, Yusuke Sakai, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe,
• Abstract summary: The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs. The existing dominant approach, however, naively calculates and compares the probabilities of paired sentences using LMs. We investigate how to make the most of LLMs' grammatical knowledge to comprehensively evaluate it.
• Score: 22.76776244036282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where LMs are presented with a pair of acceptable and unacceptable sentences and required to judge which is acceptable. The existing dominant approach, however, naively calculates and compares the probabilities of paired sentences using LMs. Additionally, large language models (LLMs) have yet to be thoroughly examined in this field. We thus investigate how to make the most of LLMs' grammatical knowledge to comprehensively evaluate it. Through extensive experiments of nine judgment methods in English and Chinese, we demonstrate that a probability readout method, in-template LP, and a prompting-based method, Yes/No probability computing, achieve particularly high performance, surpassing the conventional approach. Our analysis reveals their different strengths, e.g., Yes/No probability computing is robust against token-length bias, suggesting that they harness different aspects of LLMs' grammatical knowledge. Consequently, we recommend using diverse judgment methods to evaluate LLMs comprehensively.

Related papers

• Learning-From-Mistakes Prompting for Indigenous Language Translation [3.7790255156708397]
  This paper presents techniques to improve extremely low-resourced indigenous language translations. Our approaches are grounded in the use of a datastore consisting of a limited number of parallel translation examples. We harness the potential of LLMs and in-context learning techniques in such a setting for using LLMs as universal translators.
  arXiv  Detail & Related papers  (2024-07-18T09:41:20Z)
• TasTe: Teaching Large Language Models to Translate through Self-Reflection [82.83958470745381]
  Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. We propose the TasTe framework, which stands for translating through self-reflection. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T17:21:21Z)
• Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach [0.0]
  Large Language Models (LLMs) produce inaccurate outputs, also known as hallucinations. This paper introduces a supervised learning approach employing only four numerical features derived from tokens and vocabulary probabilities obtained from other evaluators. The method yields promising results, surpassing state-of-the-art outcomes in multiple tasks across three different benchmarks.
  arXiv  Detail & Related papers  (2024-05-30T03:00:47Z)
• Language Models can Evaluate Themselves via Probability Discrepancy [38.54454263880133]
  We propose a new self-evaluation method ProbDiff for assessing the efficacy of various Large Language Models (LLMs) It uniquely utilizes the LLMs being tested to compute the probability discrepancy between the initial response and its revised versions. Our findings reveal that ProbDiff achieves results on par with those obtained from evaluations based on GPT-4.
  arXiv  Detail & Related papers  (2024-05-17T03:50:28Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Likelihood-based Mitigation of Evaluation Bias in Large Language Models [37.07596663793111]
  Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. It is possible that there might be a likelihood bias if LLMs are used for evaluation.
  arXiv  Detail & Related papers  (2024-02-25T04:52:02Z)
• Benchmarking LLMs via Uncertainty Quantification [91.72588235407379]
  The proliferation of open-source Large Language Models (LLMs) has highlighted the urgent need for comprehensive evaluation methods. We introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our findings reveal that: I) LLMs with higher accuracy may exhibit lower certainty; II) Larger-scale LLMs may display greater uncertainty compared to their smaller counterparts; and III) Instruction-finetuning tends to increase the uncertainty of LLMs.
  arXiv  Detail & Related papers  (2024-01-23T14:29:17Z)
• Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity [61.54815512469125]
  This survey addresses the crucial issue of factuality in Large Language Models (LLMs) As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
  arXiv  Detail & Related papers  (2023-10-11T14:18:03Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• LLM-Rec: Personalized Recommendation via Prompting Large Language Models [62.481065357472964]
  Large language models (LLMs) have showcased their ability to harness commonsense knowledge and reasoning. Recent advances in large language models (LLMs) have showcased their remarkable ability to harness commonsense knowledge and reasoning. This study introduces a novel approach, coined LLM-Rec, which incorporates four distinct prompting strategies of text enrichment for improving personalized text-based recommendations.
  arXiv  Detail & Related papers  (2023-07-24T18:47:38Z)

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.