Pith. sign in

REVIEW 5 cited by

Do Llamas Work in English? On the Latent Language of Multilingual Transformers

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 2402.10588 v4 pith:FDD53OXA submitted 2024-02-16 cs.CL cs.CY

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

We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language -- a question of key importance for understanding how language models function and the origins of linguistic bias. Focusing on the Llama-2 family of transformer models, our study uses carefully constructed non-English prompts with a unique correct single-token continuation. From layer to layer, transformers gradually map an input embedding of the final prompt token to an output embedding from which next-token probabilities are computed. Tracking intermediate embeddings through their high-dimensional space reveals three distinct phases, whereby intermediate embeddings (1) start far away from output token embeddings; (2) already allow for decoding a semantically correct next token in the middle layers, but give higher probability to its version in English than in the input language; (3) finally move into an input-language-specific region of the embedding space. We cast these results into a conceptual model where the three phases operate in "input space", "concept space", and "output space", respectively. Crucially, our evidence suggests that the abstract "concept space" lies closer to English than to other languages, which may have important consequences regarding the biases held by multilingual language models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models

    cs.CL 2025-10 conditional novelty 7.0 of 10

    ChiKhaPo is an 8-subtask benchmark that measures word-level comprehension and generation in 2,700+ languages and shows state-of-the-art models perform poorly on low-resource languages.

  2. 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.

  3. Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting

    cs.AI 2025-10 conditional novelty 6.0 of 10

    An early-exit rule with a zero-shot fallback, calibrated by Learn-then-Test risk control, keeps the average loss from corrupted in-context demonstrations under a preset bound.

  4. BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A self-supervision method makes multimodal LLMs align their input image embeddings with the model's own refined internal representations, improving visual QA scores over LLaVA baselines.

  5. Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    Selective fine-tuning of language-specific shallow layers identified by neuron activation analysis improves multilingual vision-language performance with only 14% of parameters tuned.

Pith tools