Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language

• URL: http://arxiv.org/abs/2510.06378v1
• Date: Tue, 07 Oct 2025 18:56:45 GMT
• Title: Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
• Authors: Angie Boggust, Donghao Ren, Yannick Assogba, Dominik Moritz, Arvind Satyanarayan, Fred Hohman,
• Abstract summary: We introduce semantices, structured language descriptions of large language model (LLM) features.<n>We find that semantices match the accuracy of natural language while yielding more concise and consistent feature descriptions.
• Score: 29.636642657652455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, these natural language feature descriptions are often vague, inconsistent, and require manual relabeling. In response, we introduce semantic regexes, structured language descriptions of LLM features. By combining primitives that capture linguistic and semantic feature patterns with modifiers for contextualization, composition, and quantification, semantic regexes produce precise and expressive feature descriptions. Across quantitative benchmarks and qualitative analyses, we find that semantic regexes match the accuracy of natural language while yielding more concise and consistent feature descriptions. Moreover, their inherent structure affords new types of analyses, including quantifying feature complexity across layers, scaling automated interpretability from insights into individual features to model-wide patterns. Finally, in user studies, we find that semantic regex descriptions help people build accurate mental models of LLM feature activations.

Related papers

• Towards Corpus-Grounded Agentic LLMs for Multilingual Grammatical Analysis [0.5545791216381869]
  We explore how agentic large language models (LLMs) can streamline the systematic analysis of annotated corpora.<n>We introduce an agentic framework for corpus-grounded grammatical analysis that integrates concepts such as natural-language task interpretation.<n>We test the system on multilingual grammatical tasks inspired by the World Atlas of Language Structures (WALS)
  arXiv  Detail & Related papers  (2025-11-28T21:27:58Z)
• Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability [31.30541946703775]
  Translating internal representations and computations of models into concepts that humans can understand is a key goal of interpretability.<n>Recent dictionary learning methods such as Sparse Autoencoders provide a promising route to discover human-interpretable features.<n>But they exhibit a bias towards shallow, token-specific, or noisy features, such as "the phrase 'The' at the start of sentences"
  arXiv  Detail & Related papers  (2025-10-30T17:59:30Z)
• RELIC: Evaluating Compositional Instruction Following via Language Recognition [37.49115450182637]
  Large language models (LLMs) are increasingly expected to perform tasks based only on a specification of the task provided in context.<n>We introduce the Recognition of Languages In-Context (RELIC) framework to evaluate instruction following using language recognition.
  arXiv  Detail & Related papers  (2025-06-05T16:17:24Z)
• Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition [50.86415025650168]
  Masked image modeling (MIM) tends to exploit local structures to reconstruct visual patterns, resulting in limited linguistic knowledge.<n>We propose a Linguistics-aware Masked Image Modeling (LMIM) approach, which channels the linguistic information into the decoding process of MIM through a separate branch.
  arXiv  Detail & Related papers  (2025-03-24T14:53:35Z)
• Unnatural Languages Are Not Bugs but Features for LLMs [92.8332103170009]
  Large Language Models (LLMs) have been observed to process non-human-readable text sequences, such as jailbreak prompts.<n>We present a systematic investigation challenging this perception, demonstrating that unnatural languages contain latent features usable by models.
  arXiv  Detail & Related papers  (2025-03-02T12:10:17Z)
• DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment [82.86363991170546]
  We propose a Descriptive Speech-Text Alignment approach that leverages speech captioning to bridge the gap between speech and text modalities. Our model demonstrates superior performance on the Dynamic-SUPERB benchmark, particularly in generalizing to unseen tasks. These findings highlight the potential to reshape instruction-following SLMs by incorporating descriptive rich, speech captions.
  arXiv  Detail & Related papers  (2024-06-27T03:52:35Z)
• Syntactic Substitutability as Unsupervised Dependency Syntax [31.488677474152794]
  We model a more general property implicit in the definition of dependency relations, syntactic substitutability. This property captures the fact that words at either end of a dependency can be substituted with words from the same category. We show that increasing the number of substitutions used improves parsing accuracy on natural data.
  arXiv  Detail & Related papers  (2022-11-29T09:01:37Z)
• Prompting Language Models for Linguistic Structure [73.11488464916668]
  We present a structured prompting approach for linguistic structured prediction tasks. We evaluate this approach on part-of-speech tagging, named entity recognition, and sentence chunking. We find that while PLMs contain significant prior knowledge of task labels due to task leakage into the pretraining corpus, structured prompting can also retrieve linguistic structure with arbitrary labels.
  arXiv  Detail & Related papers  (2022-11-15T01:13:39Z)
• BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing [55.058258437125524]
  We introduce BenchCLAMP, a Benchmark to evaluate Constrained LAnguage Model Parsing. We benchmark eight language models, including two GPT-3 variants available only through an API. Our experiments show that encoder-decoder pretrained language models can achieve similar performance or surpass state-of-the-art methods for syntactic and semantic parsing when the model output is constrained to be valid.
  arXiv  Detail & Related papers  (2022-06-21T18:34:11Z)
• AUTOLEX: An Automatic Framework for Linguistic Exploration [93.89709486642666]
  We propose an automatic framework that aims to ease linguists' discovery and extraction of concise descriptions of linguistic phenomena. Specifically, we apply this framework to extract descriptions for three phenomena: morphological agreement, case marking, and word order. We evaluate the descriptions with the help of language experts and propose a method for automated evaluation when human evaluation is infeasible.
  arXiv  Detail & Related papers  (2022-03-25T20:37:30Z)
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [73.06435180872293]
  We construct a recurrent neural network predictor based on byte embeddings and convolutional layers. We show that some features from various linguistic types can be predicted reliably.
  arXiv  Detail & Related papers  (2020-04-30T21:00:53Z)

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.