Pith. sign in

REVIEW 4 cited by

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages

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 2501.06346 v2 pith:RSHOSWZR submitted 2025-01-10 cs.CL

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

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In this work, we explore the extent to which LLMs share representations of morphsyntactic concepts such as grammatical number, gender, and tense across languages. We train sparse autoencoders on Llama-3-8B and Aya-23-8B, and demonstrate that abstract grammatical concepts are often encoded in feature directions shared across many languages. We use causal interventions to verify the multilingual nature of these representations; specifically, we show that ablating only multilingual features decreases classifier performance to near-chance across languages. We then use these features to precisely modify model behavior in a machine translation task; this demonstrates both the generality and selectivity of these feature's roles in the network. Our findings suggest that even models trained predominantly on English data can develop robust, cross-lingual abstractions of morphosyntactic concepts.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Semantic Primes as Explanans for Emotion in Large Language Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    NSM semantic primes are more recoverable, more causally effective, and behaviorally more interchangeable with emotions than appraisal dimensions in four instruction-tuned LLMs.

  2. Rethinking Cross-lingual Gaps from a Statistical Viewpoint

    cs.CL 2025-10 conditional novelty 6.0 of 10

    Cross-lingual accuracy gaps in LLMs are dominated by higher response variance in target languages, not missing knowledge; ensembling and variance-reduction prompts shrink the gap.

  3. The Emergence of Abstract Thought in Large Language Models Beyond Any Language

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Across 20 open LLMs, shared multilingual neurons grow in number and per-neuron importance over release generations, which the authors interpret as evidence of language-agnostic abstract thought and use to guide neuron...

  4. How Syntax Specialization Emerges in Language Models

    cs.CL 2025-05 reject novelty 5.0 of 10

    Syntactic specialization in language models emerges gradually during training, concentrates in particular layers, and appears to stabilize after roughly 16 million tokens.

Pith tools