Pith. sign in

Paper Citation Record · LEDGER

Do Multilingual LLMs Think In English?

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 18 inbound Pith citation observations for arXiv:2502.15603.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.15603 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 18 of 18 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:52:42.296315Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T15:18:32.897299Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 73bcba04-0a0c-4209-90a4-ba4106cbc0f7 · inbound

Language Specific Knowledge: Do Models Know Better in X than in English? cites this paper.

Language Specific Knowledge: Do Models Know Better in X than in English? Do Multilingual LLMs Think In English?

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-05-22T14:51:42.685117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-22T14:48:29.590965Z digest=sha256:ae38fdb5e0006e2defb7e960b00c48d80988dc3f5d460d1551a72995820a0ad4

Observation aea46989-4354-4d6f-9956-56ec246d3fe1 · inbound

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? cites this paper.

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? Do Multilingual LLMs Think In English?

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T14:52:42.296315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:52:42.296315Z digest=sha256:4e02f2d5aac1fca310c3233445eb802b6bdf5979d6b18d1fc598a15d8341f63f

Observation 1c4aa35e-10fc-439b-9b03-376fafafeb3c · inbound

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline cites this paper.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Do Multilingual LLMs Think In English?

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T13:58:19.134805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:58:19.134805Z digest=sha256:00ab46d63c38c3de33055764249f953350b89c87f7e2f41bb7001a64b032f309

Observation 0bccd2aa-088b-41b6-8a0f-133d24fa1a02 · inbound

Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance cites this paper.

Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance Do Multilingual LLMs Think In English?

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T13:35:58.540028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:35:58.540028Z digest=sha256:fd61aa1310c061822c612a58ddd75d5169a8c24c8a986cf443647f21f00406e9

Observation fd4df91b-1554-4187-9ee8-39dab632f88b · inbound

The Emergence of Abstract Thought in Large Language Models Beyond Any Language cites this paper.

The Emergence of Abstract Thought in Large Language Models Beyond Any Language Do Multilingual LLMs Think In English?

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T04:43:43.491399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:43:43.491399Z digest=sha256:e595bb569c6c09764504153534c9fe1fc558bf745a5ee5d79ec6cf4a05e05fbd

Observation de15f970-bb42-4964-8ad0-1b1bbc0b89aa · inbound

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs cites this paper.

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs Do Multilingual LLMs Think In English?

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T23:49:02.577676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:49:02.577676Z digest=sha256:09b67f33ec7da9e6bded6c6efe8f7932c4dd4bbf4b2b2c1ee4faa53db3ed0651

Observation 839deaa6-6b11-4eb1-8ebc-53e496c089ad · inbound

Text2Cypher Across Languages: Evaluating and Finetuning LLMs cites this paper.

Text2Cypher Across Languages: Evaluating and Finetuning LLMs Do Multilingual LLMs Think In English?

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T22:28:16.437656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T22:28:16.437656Z digest=sha256:de311b63c3ae2fc80523d534e429a36627981173ba85d67b4fb159f5f206eb2f

Observation e9387b31-a18e-498e-ac74-2c0172a9dd29 · inbound

Humans overrely on overconfident language models, across languages cites this paper.

Humans overrely on overconfident language models, across languages Do Multilingual LLMs Think In English?

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T19:14:34.333824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:14:34.333824Z digest=sha256:7780ee7a0f3193846da853e89058442f549ddebb7544d1316345dffaceb90da0

Observation caa56a93-fa78-4e9b-9aa5-bc63d49aea59 · inbound

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation cites this paper.

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation Do Multilingual LLMs Think In English?

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T16:36:26.844939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T16:36:26.844939Z digest=sha256:a609f4dbd509bcf1d2c4664b390ce3259a368964bd01ad0dca135b0de5796baf

Observation 010740b8-1f5c-4f8b-856d-0d139876f36d · inbound

What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations cites this paper.

What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations Do Multilingual LLMs Think In English?

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T13:48:10.365399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:48:10.365399Z digest=sha256:4543d28e80fed92a884fab9e17de6e2b74fb0415192cdf0d0fff185270b323b0

Observation bc0dc047-d7b8-4b90-a7ea-6cbefd6d4737 · inbound

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla cites this paper.

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla Do Multilingual LLMs Think In English?

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T19:45:17.563725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T19:45:17.563725Z digest=sha256:8f74e39d18d12b26bff4bf07e626a48637abe8901a7bf153dea5240603ea2433

Observation eefd1a05-1d8f-4019-8888-91a23741f823 · inbound

Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG cites this paper.

Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG Do Multilingual LLMs Think In English?

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-04T16:31:24.591157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T16:31:24.591157Z digest=sha256:a62077db4899fb7a2a336ef6ea213d969024e2cbf707a5b8bae7e6900e1c6036

Observation f80a0729-bdb8-4df4-9ba3-a977c5547e98 · inbound

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting cites this paper.

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting Do Multilingual LLMs Think In English?

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T12:45:26.665289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T12:45:26.665289Z digest=sha256:03e0754ee49c3e27939e828a437d4609290db10466d423f1adead1c631288a3a

Observation 8e4f84ed-7237-4912-aab5-4102738ac56c · inbound

Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic cites this paper.

Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic Do Multilingual LLMs Think In English?

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:55:56.673617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-18T05:54:04.948619Z digest=sha256:c957edbc8eae901b1f2253005270b265175f9ecc33410c642e87b4e1a31d49be

Observation 1589482d-b47c-425c-af84-c6d2a9371cfb · inbound

English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training cites this paper.

English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training Do Multilingual LLMs Think In English?

Reference 12

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T11:11:01.323195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-10T15:08:32.517020Z digest=sha256:445b46a54c8a2393928d8a8ba7c704882aea881f4f01bb6ce77f8d7fdabcef8d

Observation 4f0c3725-fca2-4660-ad0a-82262e3d25c8 · inbound

TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B cites this paper.

TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B Do Multilingual LLMs Think In English?

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T15:18:32.898710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-07-03T15:09:14.993998Z digest=sha256:a92a77934375ee44b2a221e781035c826551df771606c2ef1362cb9e53bb0abb

Observation 8801f0f7-b864-47ba-824f-40022bfc91e0 · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Do Multilingual LLMs Think In English?

Reference 148

Resolution
unresolved
no resolver link, observed 2026-08-01T23:15:30.786286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T23:15:30.786286Z digest=sha256:ac7d51da50df81644346fa63c36347bde06efdb6bff0a9eb3a639e4fa1e095ba

Observation 19674b2f-70b5-4f7b-b551-1294fc8c85e1 · inbound

Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference cites this paper.

Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference Do Multilingual LLMs Think In English?

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T13:56:22.641374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T13:56:22.641374Z digest=sha256:5063ca792c9c090a09bc8cfa0d2ca6b7698fe07394ab3f6a20da31bf3b2953df