Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments

• URL: http://arxiv.org/abs/2505.22137v1
• Date: Wed, 28 May 2025 09:00:56 GMT
• Title: Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments
• Authors: Marc Feger, Katarina Boland, Stefan Dietze,
• Abstract summary: This study offers the first large-scale re-evaluation of such state-of-the-art models.<n>We evaluate four transformers, three standard and one enhanced with contrastive pre-training for better generalization.<n>Our findings show that, to varying degrees, these models tend to rely on lexical shortcuts tied to content words.
• Score: 3.4163020595590106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Identifying arguments is a necessary prerequisite for various tasks in automated discourse analysis, particularly within contexts such as political debates, online discussions, and scientific reasoning. In addition to theoretical advances in understanding the constitution of arguments, a significant body of research has emerged around practical argument mining, supported by a growing number of publicly available datasets. On these benchmarks, BERT-like transformers have consistently performed best, reinforcing the belief that such models are broadly applicable across diverse contexts of debate. This study offers the first large-scale re-evaluation of such state-of-the-art models, with a specific focus on their ability to generalize in identifying arguments. We evaluate four transformers, three standard and one enhanced with contrastive pre-training for better generalization, on 17 English sentence-level datasets as most relevant to the task. Our findings show that, to varying degrees, these models tend to rely on lexical shortcuts tied to content words, suggesting that apparent progress may often be driven by dataset-specific cues rather than true task alignment. While the models achieve strong results on familiar benchmarks, their performance drops markedly when applied to unseen datasets. Nonetheless, incorporating both task-specific pre-training and joint benchmark training proves effective in enhancing both robustness and generalization.

Related papers

• TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data [9.390415313514762]
  TARGA is a framework that generates high-relevance synthetic data without manual annotation.<n>It substantially outperforms existing non-fine-tuned methods that utilize close-sourced model.<n>It exhibits superior sample efficiency, robustness, and generalization capabilities under non-I.I.D. settings.
  arXiv  Detail & Related papers  (2024-12-27T09:16:39Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue [92.01165203498299]
  Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange. This paper argues that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research.
  arXiv  Detail & Related papers  (2022-10-10T05:51:40Z)
• Contextualization and Generalization in Entity and Relation Extraction [0.0]
  We study the behaviour of state-of-the-art models regarding generalization to facts unseen during training. Traditional benchmarks present important lexical overlap between mentions and relations used for training and evaluating models. We propose empirical studies to separate performance based on mention and relation overlap with the training set.
  arXiv  Detail & Related papers  (2022-06-15T14:16:42Z)
• Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge [59.22170796793179]
  Transformers Language Models (TLMs) were tested on a benchmark for the textitdynamic estimation of thematic fit Our results show that TLMs can reach performances that are comparable to those achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge.
  arXiv  Detail & Related papers  (2021-07-22T20:52:26Z)
• ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining [61.82562838486632]
  We crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads. We benchmark state-of-the-art models on our datasets and analyze characteristics associated with the data.
  arXiv  Detail & Related papers  (2021-06-01T22:17:13Z)
• Do Fine-tuned Commonsense Language Models Really Generalize? [8.591839265985412]
  We study the generalization issue in detail by designing and conducting a rigorous scientific study. We find clear evidence that fine-tuned commonsense language models still do not generalize well, even with moderate changes to the experimental setup.
  arXiv  Detail & Related papers  (2020-11-18T08:52:49Z)
• High-order Semantic Role Labeling [86.29371274587146]
  This paper introduces a high-order graph structure for the neural semantic role labeling model. It enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models.
  arXiv  Detail & Related papers  (2020-10-09T15:33:54Z)
• ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning [85.33459673197149]
  We introduce a new Reading dataset requiring logical reasoning (ReClor) extracted from standardized graduate admission examinations. In this paper, we propose to identify biased data points and separate them into EASY set and the rest as HARD set. Empirical results show that state-of-the-art models have an outstanding ability to capture biases contained in the dataset with high accuracy on EASY set. However, they struggle on HARD set with poor performance near that of random guess, indicating more research is needed to essentially enhance the logical reasoning ability of current models.
  arXiv  Detail & Related papers  (2020-02-11T11:54:29Z)

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.