Linguistically Grounded Analysis of Language Models using Shapley Head Values (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for probing language models for morphosyntactic constructions are not well understood . language models gain knowledge of grammatical phenomena during pretraining, but exactly how this knowledge is encoded is not well established. |
| Approach: | They propose a method for probing language models via Shapley Head Values . they use a BLiMP dataset to test their method on linguistic constructions based on a Shaply Head Value method . |
| Outcome: | The proposed method can be used to investigate linguistic knowledge in language models . it shows that attention heads responsible for processing related linguistic phenomena cluster together . |
Similar Papers
Using Shapley interactions to understand how models use structure (2025.acl-long)
Copied to clipboard
| Challenge: | Language models are intricately structured systems, and attribution measures are important for understanding how they combine features to influence outputs. |
| Approach: | They use Shapley Taylor interaction indices to examine how language and speech models internally relate and structure their inputs. |
| Outcome: | The proposed methods show that language models encode phonetic interactions . they show that the inputs are more entangled for pairs where a consonant influences a vowel or approximant . |
Feature Interactions Reveal Linguistic Structure in Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing features attribution methods for post-hoc interpretability ignore the existence of interactions between the effects of features on the prediction. |
| Approach: | They propose a grey box method to train models to perfection on a formal language classification task using PCFGs. |
| Outcome: | The proposed methods are able to uncover the grammatical rules acquired by the model under specific configurations and provide novel insights into the linguistic structure of the target models. |
Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers (2023.eacl-main)
Copied to clipboard
| Challenge: | Multilingual transformer-based models demonstrate remarkable zero and few-shot transfer across languages by learning and reusing language-agnostic features. |
| Approach: | They propose to prune attention heads from a fixed model to reduce interference as a model acquires more languages. |
| Outcome: | The proposed model can reduce interference by pruning language-specific attention heads. |
Do Neural Language Models Show Preferences for Syntactic Formalisms? (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work on interpretability of deep neural language models concludes that many properties of natural language syntax are encoded in their representational spaces. |
| Approach: | They propose to examine whether syntactic structure adheres to a surface-syntactical or deep syntaktic style of analysis. |
| Outcome: | The proposed model prefers Universal Dependencies (UD) over Surface-Syntactic Universal Dependency (SUD) with interesting variations across languages and layers. |
Attention Can Reflect Syntactic Structure (If You Let It) (2021.eacl-main)
Copied to clipboard
| Challenge: | a recent study has attempted to decode linguistic structure from the Transformer . but, much of the work focused on English, a language with rigid word order and a lack of inflectional morphology. |
| Approach: | They propose to fine-tune a feature encoder for BERT to learn linguistic structure from its multi-head attention mechanism. |
| Outcome: | The proposed model can decode full trees above baseline accuracy from single attention heads across languages. |
Overestimation of Syntactic Representation in Neural Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Several testing methodologies have been developed to probe models’ syntactic representations. |
| Approach: | They propose a method to determine syntactic structure by training a model on strings generated according to a template and testing its ability to distinguish between similar ones with different syntax. |
| Outcome: | The proposed method reproduces positive results with two non-syntactic baseline language models: an n-gram model and an LSTM model trained on scrambled inputs. |
Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in language models have demonstrated their ability to process linguistic expressions with complex syntactic structures. |
| Approach: | They investigate whether language models employ shared neural mechanisms across different constructions by applying causal interpretability methods at a granular level. |
| Outcome: | The proposed model performance improves on acceptability judgment benchmarks. |
Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a popular approach to decompose the neural bases of language requires large and costly data sets to obtain. |
| Approach: | They propose a model-based approach to decompose the neural bases of language that can be used to correlate brain responses to different stimuli. |
| Outcome: | The proposed model-based approach replicates the seminal study of Lerner et al. (2011), which revealed the hierarchy of language areas by comparing the functional-magnetic resonance imaging (fMRI) of seven subjects listening to 7min of both regular and scrambled narratives. |
Extracting Linguistic Information from Large Language Models: Syntactic Relations and Derivational Knowledge (2025.emnlp-main)
Copied to clipboard
| Challenge: | Using large language models, we study their morphosyntactic competence and generalization capabilities. |
| Approach: | They propose to use morphosyntactic tasks to study their linguistic knowledge and generalization capabilities to extract different types of morphological structure for typologically diverse languages. |
| Outcome: | The proposed models outperform GPT-4o and LLaMA 3.3-70B in all diagnostic tasks, but show little evidence of abstract morphological rule learning. |
WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language (2022.acl-short)
Copied to clipboard
| Challenge: | Signed Language Processing (SLP) is a major form of NLP, but has been overlooked by the NLP community. |
| Approach: | They leverage existing resources to construct a large-scale dataset of American Sign Language signs annotated with six different phonological properties. |
| Outcome: | The proposed model outperforms existing approaches on signs unobserved during training. |