Feature Interactions Reveal Linguistic Structure in Language Models

• URL: http://arxiv.org/abs/2306.12181v1
• Date: Wed, 21 Jun 2023 11:24:41 GMT
• Title: Feature Interactions Reveal Linguistic Structure in Language Models
• Authors: Jaap Jumelet, Willem Zuidema
• Abstract summary: 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.
• Score: 2.0178765779788495
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study feature interactions in the context of feature attribution methods for post-hoc interpretability. In interpretability research, getting to grips with feature interactions is increasingly recognised as an important challenge, because interacting features are key to the success of neural networks. Feature interactions allow a model to build up hierarchical representations for its input, and might provide an ideal starting point for the investigation into linguistic structure in language models. However, uncovering the exact role that these interactions play is also difficult, and a diverse range of interaction attribution methods has been proposed. In this paper, we focus on the question which of these methods most faithfully reflects the inner workings of the target models. We work out a grey box methodology, in which we train models to perfection on a formal language classification task, using PCFGs. We show that under specific configurations, some methods are indeed able to uncover the grammatical rules acquired by a model. Based on these findings we extend our evaluation to a case study on language models, providing novel insights into the linguistic structure that these models have acquired.

Related papers

• Linguistically Grounded Analysis of Language Models using Shapley Head Values [2.914115079173979]
  We investigate the processing of morphosyntactic phenomena by leveraging a recently proposed method for probing language models via Shapley Head Values (SHVs) Using the English language BLiMP dataset, we test our approach on two widely used models, BERT and RoBERTa, and compare how linguistic constructions are handled. Our results show that SHV-based attributions reveal distinct patterns across both models, providing insights into how language models organize and process linguistic information.
  arXiv  Detail & Related papers  (2024-10-17T09:48:08Z)
• 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)
• SINC: Self-Supervised In-Context Learning for Vision-Language Tasks [64.44336003123102]
  We propose a framework to enable in-context learning in large language models. A meta-model can learn on self-supervised prompts consisting of tailored demonstrations. Experiments show that SINC outperforms gradient-based methods in various vision-language tasks.
  arXiv  Detail & Related papers  (2023-07-15T08:33:08Z)
• Topics in Contextualised Attention Embeddings [7.6650522284905565]
  Recent work has demonstrated that conducting clustering on the word-level contextual representations from a language model emulates word clusters that are discovered in latent topics of words from Latent Dirichlet Allocation. The important question is how such topical word clusters are automatically formed, through clustering, in the language model when it has not been explicitly designed to model latent topics. Using BERT and DistilBERT, we find that the attention framework plays a key role in modelling such word topic clusters.
  arXiv  Detail & Related papers  (2023-01-11T07:26:19Z)
• Negation, Coordination, and Quantifiers in Contextualized Language Models [4.46783454797272]
  We explore whether the semantic constraints of function words are learned and how the surrounding context impacts their embeddings. We create suitable datasets, provide new insights into the inner workings of LMs vis-a-vis function words and implement an assisting visual web interface for qualitative analysis.
  arXiv  Detail & Related papers  (2022-09-16T10:01:11Z)
• Language Model Cascades [72.18809575261498]
  Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. Cases with control flow and dynamic structure require techniques from probabilistic programming. We formalize several existing techniques from this perspective, including scratchpads / chain of thought, verifiers, STaR, selection-inference, and tool use.
  arXiv  Detail & Related papers  (2022-07-21T07:35:18Z)
• Compositional Generalization in Grounded Language Learning via Induced Model Sparsity [81.38804205212425]
  We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We design an agent that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations.
  arXiv  Detail & Related papers  (2022-07-06T08:46:27Z)
• Probing via Prompting [71.7904179689271]
  This paper introduces a novel model-free approach to probing, by formulating probing as a prompting task. We conduct experiments on five probing tasks and show that our approach is comparable or better at extracting information than diagnostic probes. We then examine the usefulness of a specific linguistic property for pre-training by removing the heads that are essential to that property and evaluating the resulting model's performance on language modeling.
  arXiv  Detail & Related papers  (2022-07-04T22:14:40Z)
• 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)
• Probing Task-Oriented Dialogue Representation from Language Models [106.02947285212132]
  This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We fine-tune a feed-forward layer as the classifier probe on top of a fixed pre-trained language model with annotated labels in a supervised way.
  arXiv  Detail & Related papers  (2020-10-26T21:34:39Z)

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.