A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability

• URL: http://arxiv.org/abs/2608.29034v1
• Date: Sat, 29 Aug 2026 04:00:46 GMT
• Title: A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability
• Abstract summary: We propose using unified Product Representations (TPRs) as a unifying hypothesis.<n>We show, both mathematically and empirically, that TPRs can unify several prior interpretability methods.<n> Empirically, we apply the derivations to a range of different models to construct instances of each of the above interpretability methods.
• Score: 5.242425502046959
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A wide range of methods have been proposed for interpreting language models, delivering important insights into their inner workings. However, different methods and their resulting insights stand in relative isolation: what could the underlying structure of language models be, such that they give rise to all our interpretations? In this work, we propose using Tensor Product Representations (TPRs) as a unifying hypothesis. TPRs give a concrete proposal for how compositional structure could be represented in vector space --- as filler-role bindings. We show, both mathematically and empirically, that TPRs can unify several prior interpretability methods: additive analogies, linear probing, sparse autoencoders, and activation patching. Mathematically, we show that these methods can all be derived from TPRs. Empirically, we apply the derivations to a range of different models --- from small toy models to LLMs --- to construct instances of each of the above interpretability methods; these constructed variants perform comparably to their standard variants. We view this work as a step toward what interpretability will ideally provide: a unified account of the nature of neural networks, corroborated not just by individual observations but also by an explanation of the connections between them.

Related papers

• Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models [6.390475802910619]
  We show that representations learned across models trained on the same data can be expressed as linear combinations of a emphuniversal set of basis features.<n>These basis features underlie the learning task itself and remain consistent across models, regardless of scale.
  arXiv  Detail & Related papers  (2025-05-31T17:45:18Z)
• Explaining Text Similarity in Transformer Models [52.571158418102584]
  Recent advances in explainable AI have made it possible to mitigate limitations by leveraging improved explanations for Transformers. We use BiLRP, an extension developed for computing second-order explanations in bilinear similarity models, to investigate which feature interactions drive similarity in NLP models. Our findings contribute to a deeper understanding of different semantic similarity tasks and models, highlighting how novel explainable AI methods enable in-depth analyses and corpus-level insights.
  arXiv  Detail & Related papers  (2024-05-10T17:11:31Z)
• Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars [36.780346257061495]
  Interpretability methods aim to understand the algorithm implemented by a trained model. We take a critical view of methods that exclusively focus on individual parts of the model.
  arXiv  Detail & Related papers  (2023-12-03T15:34:46Z)
• Meaning Representations from Trajectories in Autoregressive Models [106.63181745054571]
  We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle.
  arXiv  Detail & Related papers  (2023-10-23T04:35:58Z)
• Flow Factorized Representation Learning [109.51947536586677]
  We introduce a generative model which specifies a distinct set of latent probability paths that define different input transformations. We show that our model achieves higher likelihoods on standard representation learning benchmarks while simultaneously being closer to approximately equivariant models.
  arXiv  Detail & Related papers  (2023-09-22T20:15:37Z)
• All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations [69.3461199976959]
  We propose a model based on invertible neural networks, BERT-INN, to learn the Bijection Hypothesis. We show the advantage of BERT-INN both theoretically and through extensive experiments.
  arXiv  Detail & Related papers  (2023-05-23T22:30:43Z)
• Understanding Post-hoc Explainers: The Case of Anchors [6.681943980068051]
  We present a theoretical analysis of a rule-based interpretability method that highlights a small set of words to explain a text's decision. After formalizing its algorithm and providing useful insights, we demonstrate mathematically that Anchors produces meaningful results.
  arXiv  Detail & Related papers  (2023-03-15T17:56:34Z)
• Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models [91.3755431537592]
  Representing compositional and non-compositional phrases is critical for language understanding. We first formulate a problem of predicting the LM-internal representations of longer phrases given those of their constituents. While we would expect the predictive accuracy to correlate with human judgments of semantic compositionality, we find this is largely not the case.
  arXiv  Detail & Related papers  (2022-10-07T14:21:30Z)
• Interpreting Language Models with Contrastive Explanations [99.7035899290924]
  Language models must consider various features to predict a token, such as its part of speech, number, tense, or semantics. Existing explanation methods conflate evidence for all these features into a single explanation, which is less interpretable for human understanding. We show that contrastive explanations are quantifiably better than non-contrastive explanations in verifying major grammatical phenomena.
  arXiv  Detail & Related papers  (2022-02-21T18:32:24Z)
• DirectProbe: Studying Representations without Classifiers [21.23284793831221]
  DirectProbe studies the geometry of a representation by building upon the notion of a version space for a task. Experiments with several linguistic tasks and contextualized embeddings show that, even without training classifiers, DirectProbe can shine light into how an embedding space represents labels.
  arXiv  Detail & Related papers  (2021-04-13T02:40:26Z)
• Unnatural Language Inference [48.45003475966808]
  We find that state-of-the-art NLI models, such as RoBERTa and BART, are invariant to, and sometimes even perform better on, examples with randomly reordered words. Our findings call into question the idea that our natural language understanding models, and the tasks used for measuring their progress, genuinely require a human-like understanding of syntax.
  arXiv  Detail & Related papers  (2020-12-30T20:40:48Z)

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.