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

• URL: http://arxiv.org/abs/2408.09639v2
• Date: Fri, 07 Feb 2025 07:02:26 GMT
• Title: How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments
• Authors: Yusuke Ide, Yuto Nishida, Justin Vasselli, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe,
• Abstract summary: The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs. Recent large language models (LLMs) are trained to perform tasks via prompting, and thus, the raw probabilities they assign may not fully reflect their grammatical knowledge. This study attempts to derive more accurate judgments from LLMs using prompts and templates.
• Score: 22.76776244036282
• License:
• Abstract: The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where the LMs are presented with a pair of acceptable and unacceptable sentences and required to judge which is more acceptable. Conventional approaches directly compare sentence probabilities assigned by LMs, but recent large language models (LLMs) are trained to perform tasks via prompting, and thus, the raw probabilities they assign may not fully reflect their grammatical knowledge. In this study, we attempt to derive more accurate acceptability judgments from LLMs using prompts and templates. Through extensive experiments in English and Chinese, we compare nine judgment methods and find two of them, a probability readout method -- in-template LP and a prompt-based method -- Yes/No probability computing, achieve higher accuracy than the conventional ones. Our analysis reveals that these methods excel in different linguistic phenomena, suggesting they access different aspects of LLMs' knowledge. We also find that ensembling the two methods outperforms single methods. Consequently, we recommend these techniques, either individually or ensembled, as more effective alternatives to conventional approaches for assessing grammatical knowledge in LLMs.

Related papers

• The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs [21.97227334180969]
  "LLM-as-a-judge" paradigm employs Large Language Models as annotators and evaluators in tasks traditionally performed by humans. Despite their role in shaping study results and insights, there is no standard or rigorous procedure to determine whether LLMs can replace human annotators. We propose a novel statistical procedure -- the Alternative Annotator Test (alt-test) -- that requires only a modest subset of annotated examples to justify using LLM annotations.
  arXiv  Detail & Related papers  (2025-01-19T07:09:11Z)
• 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)
• 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)
• Uncertainty Quantification for In-Context Learning of Large Language Models [52.891205009620364]
  In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.
  arXiv  Detail & Related papers  (2024-02-15T18:46:24Z)
• LM-Polygraph: Uncertainty Estimation for Language Models [71.21409522341482]
  Uncertainty estimation (UE) methods are one path to safer, more responsible, and more effective use of large language models (LLMs) We introduce LM-Polygraph, a framework with implementations of a battery of state-of-the-art UE methods for LLMs in text generation tasks, with unified program interfaces in Python. It introduces an extendable benchmark for consistent evaluation of UE techniques by researchers, and a demo web application that enriches the standard chat dialog with confidence scores.
  arXiv  Detail & Related papers  (2023-11-13T15:08:59Z)
• Knowledge Rumination for Pre-trained Language Models [77.55888291165462]
  We propose a new paradigm dubbed Knowledge Rumination to help the pre-trained language model utilize related latent knowledge without retrieving it from the external corpus. We apply the proposed knowledge rumination to various language models, including RoBERTa, DeBERTa, and GPT-3.
  arXiv  Detail & Related papers  (2023-05-15T15:47:09Z)
• Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders [85.80950708769923]
  We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models. We report substantial gains on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T13:23:16Z)
• Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese [45.80297329300326]
  We examine a methodology using neural language models (LMs) for analyzing the word order of language. We explore whether the LM-based method is valid for analyzing the word order. We conclude that LMs display sufficient word order knowledge for usage as an analysis tool.
  arXiv  Detail & Related papers  (2020-05-02T14:32:40Z)

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.