Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe

2026-05-01

AI Summary

Traditional decoding probes struggle to independently assess the contribution of individual features to language model representations and are susceptible to confounding effects arising from feature correlations. This work proposes a novel encoding probe paradigm that analyzes the information encoded in model representations by linearly reconstructing internal states from interpretable features—such as acoustic, phonological, syntactic, lexical, and speaker identity attributes. This approach enables, for the first time, disentangled evaluation of each feature’s contribution and facilitates cross-modal comparisons. Experimental results demonstrate that syntactic and lexical features provide independent contributions to representation reconstruction, whereas speaker-related effects are highly dependent on training objectives and datasets, thereby validating the method’s efficacy and complementarity to existing probing techniques.

Abstract

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of different features to model representations cannot be directly compared, and feature correlations can affect probing results. We present an Encoding Probe that reverses this direction and reconstructs internal representations of models using interpretable features. We evaluate this method on text and speech transformer models, using feature sets spanning acoustics, phonetics, syntax, lexicon, and speaker identity. Our results suggest that speaker-related effects vary strongly across different training objectives and datasets, while syntactic and lexical features contribute independently to reconstruction. These results show that the Encoding Probe provides a complementary perspective on interpreting model representations beyond decodability.

Problem

• probing
• language model representations
• feature contribution
• feature correlation
• decodability

Innovation

• Encoding Probe
• representation reconstruction
• interpretable features
• language models
• probing methodology