Linguistic Interpretability of Transformer-based Language Models: a systematic review

• URL: http://arxiv.org/abs/2504.08001v1
• Date: Wed, 09 Apr 2025 08:00:12 GMT
• Title: Linguistic Interpretability of Transformer-based Language Models: a systematic review
• Authors: Miguel López-Otal, Jorge Gracia, Jordi Bernad, Carlos Bobed, Lucía Pitarch-Ballesteros, Emma Anglés-Herrero,
• Abstract summary: Language models based on the Transformer architecture achieve excellent results in many language-related tasks.<n>However, little is known about how their internal computations help them achieve their results.<n>There is, however, a line of research -- 'interpretability' -- aiming to learn how information is encoded inside these models.
• Score: 1.3194391758295114
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little is known about how their internal computations help them achieve their results. This renders these models, as of today, a type of 'black box' systems. There is, however, a line of research -- 'interpretability' -- aiming to learn how information is encoded inside these models. More specifically, there is work dedicated to studying whether Transformer-based models possess knowledge of linguistic phenomena similar to human speakers -- an area we call 'linguistic interpretability' of these models. In this survey we present a comprehensive analysis of 160 research works, spread across multiple languages and models -- including multilingual ones -- that attempt to discover linguistic information from the perspective of several traditional Linguistics disciplines: Syntax, Morphology, Lexico-Semantics and Discourse. Our survey fills a gap in the existing interpretability literature, which either not focus on linguistic knowledge in these models or present some limitations -- e.g. only studying English-based models. Our survey also focuses on Pre-trained Language Models not further specialized for a downstream task, with an emphasis on works that use interpretability techniques that explore models' internal representations.

Related papers

• On The Landscape of Spoken Language Models: A Comprehensive Survey [144.11278973534203]
  spoken language models (SLMs) act as universal speech processing systems.<n>Work in this area is very diverse, with a range of terminology and evaluation settings.
  arXiv  Detail & Related papers  (2025-04-11T13:40:53Z)
• Holmes: A Benchmark to Assess the Linguistic Competence of Language Models [59.627729608055006]
  We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence. We use computation-based probing to examine LMs' internal representations regarding distinct linguistic phenomena. As a result, we meet recent calls to disentangle LMs' linguistic competence from other cognitive abilities.
  arXiv  Detail & Related papers  (2024-04-29T17:58:36Z)
• Understanding Cross-Lingual Alignment -- A Survey [52.572071017877704]
  Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models. We survey the literature of techniques to improve cross-lingual alignment, providing a taxonomy of methods and summarising insights from throughout the field.
  arXiv  Detail & Related papers  (2024-04-09T11:39:53Z)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• Feature Interactions Reveal Linguistic Structure in Language Models [2.0178765779788495]
  We study feature interactions in the context of feature attribution methods for post-hoc interpretability. We work out a grey box methodology, in which we train models to perfection on a formal language classification task. We show that under specific configurations, some methods are indeed able to uncover the grammatical rules acquired by a model.
  arXiv  Detail & Related papers  (2023-06-21T11:24:41Z)
• Large Linguistic Models: Investigating LLMs' metalinguistic abilities [1.0923877073891446]
  We show that OpenAI's o1 vastly outperforms other models on tasks involving drawing syntactic trees and phonological generalization.<n>We speculate that OpenAI o1's unique advantage over other models may result from the model's chain-of-thought mechanism.
  arXiv  Detail & Related papers  (2023-05-01T17:09:33Z)
• Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation [0.04199844472131922]
  We present and apply the GUI-assisted framework allowing us to easily probe a massive number of languages. Most of the regularities revealed in the mBERT model are typical for the western-European languages. Our framework can be integrated with the existing probing toolboxes, model cards, and leaderboards.
  arXiv  Detail & Related papers  (2022-10-24T13:41:17Z)
• Integrating Linguistic Theory and Neural Language Models [2.870517198186329]
  I present several case studies to illustrate how theoretical linguistics and neural language models are still relevant to each other. This thesis contributes three studies that explore different aspects of the syntax-semantics interface in language models.
  arXiv  Detail & Related papers  (2022-07-20T04:20:46Z)
• Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding [1.827510863075184]
  Curriculum is a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality.
  arXiv  Detail & Related papers  (2022-04-13T10:32:03Z)
• 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)
• Schr\"odinger's Tree -- On Syntax and Neural Language Models [10.296219074343785]
  Language models have emerged as NLP's workhorse, displaying increasingly fluent generation capabilities. We observe a lack of clarity across numerous dimensions, which influences the hypotheses that researchers form. We outline the implications of the different types of research questions exhibited in studies on syntax.
  arXiv  Detail & Related papers  (2021-10-17T18:25:23Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)

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.