Understanding the Inner Workings of Language Models Through Representation Dissimilarity

• URL: http://arxiv.org/abs/2310.14993v1
• Date: Mon, 23 Oct 2023 14:46:20 GMT
• Title: Understanding the Inner Workings of Language Models Through Representation Dissimilarity
• Authors: Davis Brown, Charles Godfrey, Nicholas Konz, Jonathan Tu, Henry Kvinge
• Abstract summary: representation dissimilarity measures are functions that measure the extent to which two model's internal representations differ. Our results suggest that dissimilarity measures are a promising set of tools for shedding light on the inner workings of language models.
• Score: 5.987278280211877
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As language models are applied to an increasing number of real-world applications, understanding their inner workings has become an important issue in model trust, interpretability, and transparency. In this work we show that representation dissimilarity measures, which are functions that measure the extent to which two model's internal representations differ, can be a valuable tool for gaining insight into the mechanics of language models. Among our insights are: (i) an apparent asymmetry in the internal representations of model using SoLU and GeLU activation functions, (ii) evidence that dissimilarity measures can identify and locate generalization properties of models that are invisible via in-distribution test set performance, and (iii) new evaluations of how language model features vary as width and depth are increased. Our results suggest that dissimilarity measures are a promising set of tools for shedding light on the inner workings of language models.

Related papers

• Sparse Auto-Encoder Interprets Linguistic Features in Large Language Models [40.12943080113246]
  We present a systematic and comprehensive causal investigation using sparse auto-encoders (SAEs) We extract a wide range of linguistic features from six dimensions. We introduce two indices-Feature Representation Confidence (FRC) and Feature Intervention Confidence (FIC)-to measure the ability of linguistic features to capture and control linguistic phenomena.
  arXiv  Detail & Related papers  (2025-02-27T18:16:47Z)
• A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models [74.48084001058672]
  The rise of foundation models has transformed machine learning research. multimodal foundation models (MMFMs) pose unique interpretability challenges beyond unimodal frameworks. This survey explores two key aspects: (1) the adaptation of LLM interpretability methods to multimodal models and (2) understanding the mechanistic differences between unimodal language models and crossmodal systems.
  arXiv  Detail & Related papers  (2025-02-22T20:55:26Z)
• 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)
• LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models [50.259006481656094]
  We present a novel interactive application aimed towards understanding the internal mechanisms of large vision-language models. Our interface is designed to enhance the interpretability of the image patches, which are instrumental in generating an answer. We present a case study of how our application can aid in understanding failure mechanisms in a popular large multi-modal model: LLaVA.
  arXiv  Detail & Related papers  (2024-04-03T23:57:34Z)
• L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models [102.00201523306986]
  We present L2CEval, a systematic evaluation of the language-to-code generation capabilities of large language models (LLMs) We analyze the factors that potentially affect their performance, such as model size, pretraining data, instruction tuning, and different prompting methods. In addition to assessing model performance, we measure confidence calibration for the models and conduct human evaluations of the output programs.
  arXiv  Detail & Related papers  (2023-09-29T17:57:00Z)
• 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)
• 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: Analyzing theoretical linguistic abilities of LLMs [7.4815059492034335]
  We show that large language models can generate coherent and valid formal analyses of linguistic data. We focus on three subfields of formal linguistics: syntax, phonology, and semantics. This line of inquiry exemplifies behavioral interpretability of deep learning, where models' representations are accessed by explicit prompting.
  arXiv  Detail & Related papers  (2023-05-01T17:09:33Z)
• Competence-Based Analysis of Language Models [21.43498764977656]
  CALM (Competence-based Analysis of Language Models) is designed to investigate LLM competence in the context of specific tasks. We develop a new approach for performing causal probing interventions using gradient-based adversarial attacks. We carry out a case study of CALM using these interventions to analyze and compare LLM competence across a variety of lexical inference tasks.
  arXiv  Detail & Related papers  (2023-03-01T08:53:36Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• Perceptual Grouping in Contrastive Vision-Language Models [59.1542019031645]
  We show how vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We propose a minimal set of modifications that results in models that uniquely learn both semantic and spatial information.
  arXiv  Detail & Related papers  (2022-10-18T17:01:35Z)
• MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models [103.9987158554515]
  MultiViz is a method for analyzing the behavior of multimodal models by scaffolding the problem of interpretability into 4 stages. We show that the complementary stages in MultiViz together enable users to simulate model predictions, assign interpretable concepts to features, perform error analysis on model misclassifications, and use insights from error analysis to debug models.
  arXiv  Detail & Related papers  (2022-06-30T18:42:06Z)
• 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)

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.