Pith. sign in

REVIEW 7 cited by

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.04986 v3 pith:AF42JF6O submitted 2024-11-07 cs.CL

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

classification cs.CL
keywords datalanguagesmodelsemanticinputsmodalitiesspaceacross
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Modern language models can process inputs across diverse languages and modalities. We hypothesize that models acquire this capability through learning a shared representation space across heterogeneous data types (e.g., different languages and modalities), which places semantically similar inputs near one another, even if they are from different modalities/languages. We term this the semantic hub hypothesis, following the hub-and-spoke model from neuroscience (Patterson et al., 2007) which posits that semantic knowledge in the human brain is organized through a transmodal semantic "hub" which integrates information from various modality-specific "spokes" regions. We first show that model representations for semantically equivalent inputs in different languages are similar in the intermediate layers, and that this space can be interpreted using the model's dominant pretraining language via the logit lens. This tendency extends to other data types, including arithmetic expressions, code, and visual/audio inputs. Interventions in the shared representation space in one data type also predictably affect model outputs in other data types, suggesting that this shared representations space is not simply a vestigial byproduct of large-scale training on broad data, but something that is actively utilized by the model during input processing.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Interleaved Speech Language Models Latently Work In Text

    cs.CL 2026-06 unverdicted novelty 7.0

    Interleaved SLMs implicitly transcribe spoken words to text tokens in middle layers (top candidate for 77% of data) before predicting in text space and returning to speech.

  2. Low-Resource Safety Failures Are Action Failures, Not Representation Failures

    cs.CL 2026-05 conditional novelty 7.0

    Low-resource safety failures are action failures because the harmfulness representation transfers but the decision calibration does not; this is fixed by recalibrating a high-resource gate with 1-4 target-language examples.

  3. How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings

    cs.CL 2026-05 unverdicted novelty 7.0

    Auto-interpretation labels for SAE features generalize poorly across languages and scripts, missing the same semantic content up to 4x more often in Serbian than English and more in Cyrillic than Latin despite determi...

  4. The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?

    cs.AI 2026-05 unverdicted novelty 7.0

    Language representations serve as the asymptotic attractor for convergence in independently trained multimodal neural networks due to feature density asymmetry.

  5. Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

    cs.CL 2026-07 conditional novelty 6.0

    Persona prompting beats CAA steering and DPO adapters at making an English-prompted LLM match its own German, Spanish, and Bulgarian answer distributions, and transfers better to cultural scenarios.

  6. Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity

    cs.LG 2025-12 unverdicted novelty 6.0

    SPON adds learnable persistent activation anchors trained via distribution matching to restore LLM accuracy under high activation sparsity by preventing representational distribution shifts.

  7. Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity

    cs.LG 2025-12 unverdicted novelty 5.0

    SPON adds a small set of trainable input-independent activation vectors as representational anchors, trained by distribution matching, to stabilize sparse activation in LLMs and recover performance lost to hidden-stat...