Disentangling concept semantics via multilingual averaging in Sparse Autoencoders

• URL: http://arxiv.org/abs/2508.14275v1
• Date: Tue, 19 Aug 2025 21:18:56 GMT
• Title: Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
• Abstract summary: We propose a method that isolates concept semantics in Large Langue Models by averaging concept activations derived via Sparse Autoencoders.<n>Using the open source Gemma Scope suite of Sparse Autoencoders, we obtain concept activations for each class and language version.<n>Our results give a strong indication that the conceptual average aligns to the true relationship between classes when compared with a single language by itself.
• Score: 3.1542695050861544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Connecting LLMs with formal knowledge representation and reasoning is a promising approach to address their shortcomings. Embeddings and sparse autoencoders are widely used to represent textual content, but the semantics are entangled with syntactic and language-specific information. We propose a method that isolates concept semantics in Large Langue Models by averaging concept activations derived via Sparse Autoencoders. We create English text representations from OWL ontology classes, translate the English into French and Chinese and then pass these texts as prompts to the Gemma 2B LLM. Using the open source Gemma Scope suite of Sparse Autoencoders, we obtain concept activations for each class and language version. We average the different language activations to derive a conceptual average. We then correlate the conceptual averages with a ground truth mapping between ontology classes. Our results give a strong indication that the conceptual average aligns to the true relationship between classes when compared with a single language by itself. The result hints at a new technique which enables mechanistic interpretation of internal network states with higher accuracy.

Related papers

• LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery [14.222802170483739]
  LUCID is a vision-language sparse autoencoder that learns a shared latent dictionary for image patch and text token representations.<n> LUCID yields interpretable shared features that support patch-level grounding, establish cross-modal neuron correspondence, and enhance robustness against the concept clustering problem.<n>Our analysis reveals that LUCID's shared features capture diverse semantic categories beyond objects, including actions, attributes, and abstract concepts.
  arXiv  Detail & Related papers  (2026-02-07T02:01:25Z)
• Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation [41.62404367454763]
  This paper introduces Item-ID + Oral-language Mixture-of-Experts Language Model (IDIOMoE)<n>It treats item interaction histories as a native dialect within the language space, enabling collaborative signals to be understood in the same way as natural language.<n>It demonstrates strong recommendation performance across both public and proprietary datasets.
  arXiv  Detail & Related papers  (2025-09-30T15:30:43Z)
• Multi-Sense Embeddings for Language Models and Knowledge Distillation [17.559171180573664]
  Transformer-based large language models (LLMs) rely on contextual embeddings which generate different representations for the same token depending on its surrounding context.<n>We propose multi-sense embeddings as a drop-in replacement for each token in order to capture the range of their uses in a language.
  arXiv  Detail & Related papers  (2025-04-08T13:36:36Z)
• Large Concept Models: Language Modeling in a Sentence Representation Space [62.73366944266477]
  We present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a concept.<n> Concepts are language- and modality-agnostic and represent a higher level idea or action in a flow.<n>We show that our model exhibits impressive zero-shot generalization performance to many languages.
  arXiv  Detail & Related papers  (2024-12-11T23:36:20Z)
• Tomato, Tomahto, Tomate: Measuring the Role of Shared Semantics among Subwords in Multilingual Language Models [88.07940818022468]
  We take an initial step on measuring the role of shared semantics among subwords in the encoder-only multilingual language models (mLMs) We form "semantic tokens" by merging the semantically similar subwords and their embeddings. inspections on the grouped subwords show that they exhibit a wide range of semantic similarities.
  arXiv  Detail & Related papers  (2024-11-07T08:38:32Z)
• Text-Video Retrieval with Global-Local Semantic Consistent Learning [122.15339128463715]
  We propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL) GLSCL capitalizes on latent shared semantics across modalities for text-video retrieval. Our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost.
  arXiv  Detail & Related papers  (2024-05-21T11:59:36Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations [11.008412414253662]
  Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Recent studies have shown that LLMs tend to generate unintended, inconsistent, or wrong texts as outputs. We propose a novel ensemble learning method, Interpretable Ensemble Representation Learning (IERL), that systematically combines LLM and crowdsourced knowledge representations.
  arXiv  Detail & Related papers  (2023-06-24T05:02:34Z)
• Integrating Language Guidance into Vision-based Deep Metric Learning [78.18860829585182]
  We propose to learn metric spaces which encode semantic similarities as embedding space. These spaces should be transferable to classes beyond those seen during training. This causes learned embedding spaces to encode incomplete semantic context and misrepresent the semantic relation between classes.
  arXiv  Detail & Related papers  (2022-03-16T11:06:50Z)
• FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [85.29270319872597]
  We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
  arXiv  Detail & Related papers  (2020-09-10T22:42:15Z)

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.