Pith. sign in

Paper Citation Record · LEDGER

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE

As of 5 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2605.18083.

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

pith.paper-citation-record.v1
2605.18083 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T11:09:22.027588Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

55 of 55 outbound references displayed

  • verified exact10
  • verified fuzzy24
  • unresolved2
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch19

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b43c41a1-37c0-435c-a52a-3857714b2f0c · outbound

This paper cites Longcat-flash technical report.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Longcat-flash technical report

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.566595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:9bfeed63cd2230f74e7d02c20c9f1cf2f6d58676dcfd7fa3864df4d0f187eae1

Observation b7e0e427-8aff-46a9-8be1-f92d32a1e69d · outbound

This paper cites Qwen3 Technical Report.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Qwen3 Technical Report

Reference 2

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.547792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:f32ec31b6fa8518b5825f637e7bf908051c8cdf1895d513a835aa720ff21eea7

Observation da055637-b7bc-454e-a1bd-b5bfb044c051 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.538755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:f149e9547568553691a1223cb0003ee4e9b8897d22a8f991128222cf3526e0dc

Observation 86937396-0b3d-42cc-8b1f-6e0f1f59cfac · outbound

This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Reference 4

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.563210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:94b61defa0655b73436814f7ad1be1ca72144dc4977e8c03c70a164806c187ad

Observation 74db080a-8121-4e89-8b53-c4d0fe61c6f7 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Kimi K2: Open Agentic Intelligence

Reference 5

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.550684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:42c39d48713eac8739a03158a20b9f741f80dd40678033c3598f65707a878c35

Observation f97d1fa3-6962-4de5-9d0a-15f545831323 · outbound

This paper cites A Survey on Large Language Models for Code Generation.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE A Survey on Large Language Models for Code Generation

Reference 6

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.544841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:e0681df0944749dadfaefa0171ac3cede21e67e20e49c600cd050f42a964b3ec

Observation bbd43a06-46e9-4f69-bbbe-4fb9553c514d · outbound

This paper cites A Survey on Large Language Models for Mathematical Reasoning.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE A Survey on Large Language Models for Mathematical Reasoning

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.553569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:2e839be72cab4c671f2eefd01367e79e21c20ead20aed326d4f6880fd188cd48

Observation 45a641c4-6fb3-4698-9c5f-65f2958bab27 · outbound

This paper cites Large Language Model Agent: A Survey on Methodology, Applications and Challenges.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Reference 8

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.556985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:e5f38fd1ac7a3b83692acda51bb79380adbf5cd2342c2b59a29d56303b91dbb4

Observation fec97b88-3fdb-4b37-af1a-3806371479a1 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.254847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:5163093ffc4e2f930fb28f778ddd9074544c8665b3df2020f8d436e58ad4ae02

Observation af37c868-8239-4237-8640-ce3921390fca · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 10

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.541776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:8bf76dc54f8644a2231da08efe0f31bee5c91c1d194758fbc3631ce79b26b3c4

Observation e97a6242-0e64-43ee-abcc-8da46ab0eb23 · outbound

This paper cites Advances in neural information processing systems , volume=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Advances in neural information processing systems , volume=

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.257393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:c5a665f1855f6aae20683bc1104df33f2556c9beb1eff49f91bc9d133a1d1a1a

Observation 3f32dcd5-d54e-44f6-960a-d8dce3ec7778 · outbound

This paper cites Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Reference 12

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.560212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:f1189086c9f693c92012970c8a8a3051b58a360ec7e9a12fe60f622e0a0429f8

Observation 139b034e-a26f-470f-9c34-3f4e3623ad3c · outbound

This paper cites Journal of Machine Learning Research , volume=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Journal of Machine Learning Research , volume=

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.225250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:0117902a6a3b4c7ada06cab66387daabb48c9799c6f3fbdd9e66eb969cee4747

Observation e6db72f9-3911-4f78-9d27-3d553aad3524 · outbound

This paper cites Stanford Center for Research on Foundation Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Stanford Center for Research on Foundation Models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.267872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:4399b138f2303edd1ff87bfd8e8e2d37ac980a57c01e88cdcd0db4cbd7f21d64

Observation a205da5e-2bc2-4581-91a4-1cd302fa003d · outbound

This paper cites Simple and Scalable Strategies to Continually Pre-train Large Language Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Simple and Scalable Strategies to Continually Pre-train Large Language Models

Reference 15

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.593293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:affe1b003bc2277b3ffe4e18466d22f3dc6e75b4632f71eb695af0cd22440e06

Observation b04b4fd7-fe5e-48c7-8778-d2078ae1297c · outbound

This paper cites arXiv preprint arXiv:2412.11704 , year=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE arXiv preprint arXiv:2412.11704 , year=

Reference 16

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.584279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:18e085c1dd08e3cb1cea5c7bf4b506d4a15cfa8788ac750a09a1407ae2789138

Observation 648816ef-b3eb-4684-8cb1-76e45312c3cc · outbound

This paper cites an unresolved cited work.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-05-20T11:13:26.278426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:7603a78700d1b936311d24e08b4a21f4889fd8543bdd52cf8f40077a50ad83f0

Observation c8e0a2dd-f6d7-4ae6-91f8-f6c9dc27ec8e · outbound

This paper cites International conference on machine learning , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE International conference on machine learning , pages=

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.262441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:cb375870ee061fc08b484e9a20cabf3125761b49dc43f641126db2d7962ba91b

Observation f4077d69-88e0-4ab7-be9e-e4326502e06e · outbound

This paper cites The Eleventh International Conference on Learning Representations , year=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE The Eleventh International Conference on Learning Representations , year=

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.281032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:712e2a855b6c5bfd64a941f4400d7081d7398b33daf079f1958e15e9b3e5982e

Observation 232c0c1c-b5ca-428f-91a7-2463f6b63279 · outbound

This paper cites The Llama 3 Herd of Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE The Llama 3 Herd of Models

Reference 20

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.589974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:5988e3d62a57ac851b8184a120553291e02dc6f08ff4870c4d79b85a7f88c066

Observation 37973bf8-2d55-46af-a658-a86e60871954 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.265216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:4a6657477975fbf5cc1eccdebcec976594e36353bb59d23f080ecd0d06e7295e

Observation 8037f449-5d76-416a-9d52-c88396fa9c28 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) , address=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) , address=

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.252366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:0e620f91157eb428228f284fa52414f658ae681a03338e6edceaec319acf53a9

Observation d0f4a032-4dd7-49e1-9993-191857b7e9b1 · outbound

This paper cites SC20: International Conference for High Performance Computing, Networking, Storage and Analysis , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE SC20: International Conference for High Performance Computing, Networking, Storage and Analysis , pages=

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.274560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:567587e23d53236382ca0b7f3dc070a74d3fa7c25d682f3c7942929b4ae29fac

Observation 9c65265e-e2be-427e-a18f-c02d71c8ba7e · outbound

This paper cites FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Reference 24

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.616472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:7f390382357cb1efe5a663eb304a1cd7c80e37a45ebdb10e5cf316b00edb5279

Observation f76e6b07-e605-426c-8c2b-353fc618c1fe · outbound

This paper cites CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages

Reference 25

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.613153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:07dcbc15e449b75b84eede36dd1f4bfd0223e21be7a1a4468dd87ce10fb4923e

Observation 2d81cf49-6b9d-4525-941f-e5faccb86241 · outbound

This paper cites BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.601691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:526ed21fa9e822c14b04e4caefedc9ceaf0dd3a0f05b936dd1fface79bd4c742

Observation 2db290fc-bd00-4632-983f-50814d13c33d · outbound

This paper cites The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants

Reference 27

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.604415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:a4127d96f5434fddc102c230bb0580857bbdd9fbe65904c42a12495b62f94347

Observation 0d49686b-a922-4932-9a24-f1be89314a97 · outbound

This paper cites doi:10.57967/hf/5618 , publisher =.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE doi:10.57967/hf/5618 , publisher =

Reference 28

Resolution
verified exact
doi, observed 2026-05-20T11:13:13.285061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:f908bf5f9a6f3f11ec9ae9bf64a2dd53f95e3893f790cfcab296dc1689773c1e

Observation 96b9434f-c963-46fa-a072-fa93ed61bc1f · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Transactions of the Association for Computational Linguistics , volume=

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.276477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:cbb27c4bc5216005f78c38f28d94172742f370c23e9b679b2392df3d18f65324

Observation d3ee2c7b-45a3-4d19-a758-7cb28e787b26 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 30

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.607115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:ead7a30f1dc734571ee97c7e1302634176ae04c292850b63e200e678342646ea

Observation bdd7df18-5973-4233-87a0-27718789df76 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.270548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:a10802d8e3b7b1ff8eb386a4ffc154ef6477d423c7cbadc7377d9c4357fab3d9

Observation a056dbb3-2408-4111-9eec-fb364d9997a9 · outbound

This paper cites Higher Layers Need More LoRA Experts.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Higher Layers Need More LoRA Experts

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.610080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:29ed06ba5472cfe07e32c7a20d5290eea72e71a7b5bedda51d6afe7707abfa7c

Observation 37705b6c-74f6-4b58-aa5e-92f68ff822ae · outbound

This paper cites an unresolved cited work.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-05-20T11:13:26.215318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:6884e2d8e8d8dfe5253abb44291bdefdba989821226184f09d5083840a726bcf

Observation a120cd99-c73b-4d62-a586-d6b2065a6e52 · outbound

This paper cites Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi , booktitle=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi , booktitle=

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.246105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:b11d67c50e01691a5a3f8be3aa5e4848057bdb6e0a5ebd7cad75b7b9b9dcc7dd

Observation 129227c5-abfa-46ba-8f27-9eb27e759a62 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.236549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:f9e9c461fc3ca6bd0a5dfcccb8fe7befdc18b672829d6ee967aeef134ce9ac0f

Observation f12d744c-7471-4fa3-b1c6-022bf821ebf6 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Findings of the Association for Computational Linguistics: ACL 2025 , pages=

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.240307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:9f45f65f66969d0dd631fa5456e5bb13bd07dc11334a48edb970e6a9496144f3

Observation 5603a474-0297-4298-9bfc-5382f904e3da · outbound

This paper cites 2023 , eprint=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE 2023 , eprint=

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.243715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:01457a73e6bcd1e6d49a3653215403f9df01512a41225306c0ba7e7eb77b49ef

Observation 107e081a-4be4-4a80-bc1c-159e72248d04 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Advances in Neural Information Processing Systems , volume=

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.249042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:12cc9499dd57616fecb2b531aee0d6ba26d1b4e6d8218a0f953461bb076f7138

Observation 31f7e3ad-6aa7-4b03-b095-b23a75aa8d98 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 39

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.622500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:a197078cc45b59a1419a2d71c823500d55a5c59ed271fed6dd110ed4bacaf68e

Observation b7bb08cb-e321-4053-8e03-465a642eb423 · outbound

This paper cites International conference on machine learning , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE International conference on machine learning , pages=

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.242146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:7fddc20933d0b85e12d4b5712872ca7a7d9beed5c8ddb13565bf18c5ea38ed05

Observation fae651c2-eaab-4c5f-96d5-8b204f124d09 · outbound

This paper cites Proceedings of the 36th International Conference on Neural Information Processing Systems , pages=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Proceedings of the 36th International Conference on Neural Information Processing Systems , pages=

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.243068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:013420bf1811c5981c8b5816a2e33145362cdf98ceb7c9c4583079fbb14acd0a

Observation d10fba73-cfa1-457e-a23c-7ac75188383e · outbound

This paper cites Scaling Laws for Neural Language Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Scaling Laws for Neural Language Models

Reference 42

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.619440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:6ead2bee3a92433dc76ebd1fbdd475ff8e676dec26349ccbcbd68006d0591790

Observation 71e9fc12-6f6e-411b-8a60-6d684a167396 · outbound

This paper cites 2021 , url=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE 2021 , url=

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.227568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:17bf77f8eb35157bc754e360a9440bfaf6b37b01eb2c98b1d5207d8a833fdf7e

Observation e1dbeb0b-c530-4628-a2e4-cdf848a1aac1 · outbound

This paper cites Forty-second International Conference on Machine Learning , year=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Forty-second International Conference on Machine Learning , year=

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.227827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:8872a6b70fe2345cfb3a0355413db985567c66c38620e33334d09098b29ebf60

Observation c2a91fa7-56d8-421d-842b-462ad2ca5996 · outbound

This paper cites Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.572544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:efbe91aaf80fe992624b263cad61de116eb4f51216448360f96a63ef639dee20

Observation 51c06b35-c4f5-4b37-9eeb-63a00c66905f · outbound

This paper cites Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts

Reference 46

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.581683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:6d56e5cfd2f2076743c83c7dc3548caceb57dc3b9852a327b51b37f0a0d63fa1

Observation e8e7791f-a80f-4034-993a-d8525a086c1f · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Forty-first International Conference on Machine Learning , year=

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.230075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:3bf8c95cd15f8301ea643c0baf0557968ce187950b7b00d7bc707a2325fe1d5d

Observation 3f0085eb-2add-40be-9723-9e0c4947ffde · outbound

This paper cites LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint

Reference 48

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.575242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:61e56ee9cd0aa0d75a649cd5cc9571ee476c0adb5960203c37925dbd8222bc56

Observation 6ec97621-be24-4e2f-ac7b-6d1b99718d92 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Advances in Neural Information Processing Systems , volume=

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.222926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:3a3b230f97e3db9f4c7002ceebb9683c243cefe878030606a954f7ec758df966

Observation ce2b4be7-395b-429d-8b74-42b815b11757 · outbound

This paper cites Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.569817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:0bd0b42ab1b2bd6e4326639bebc03aecd1444bbbb1f1608c9e3a4e4978ca2b17

Observation 96295a3b-53fb-48ef-909d-f2ba70c01645 · outbound

This paper cites ST-MoE: Designing Stable and Transferable Sparse Expert Models.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE ST-MoE: Designing Stable and Transferable Sparse Expert Models

Reference 51

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T11:13:13.598892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:93b7bfe8ef4c2cbf8af6fc942ed883cceef208b5412bce4c9bc1458ba25c0130

Observation a35b82e5-7756-42c2-bbba-49e0a1d5271e · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE The Thirteenth International Conference on Learning Representations , year=

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.259763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:1b06815b046d254443cf813e0ae9247265579d04a6feae0ed1f214b519fadd34

Observation 138b5651-9e5b-460c-a957-c846cbb4fbec · outbound

This paper cites Thirty-seventh Conference on Neural Information Processing Systems , year=.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Thirty-seventh Conference on Neural Information Processing Systems , year=

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T11:13:26.272636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:81d7451df58d9c1d536df73c56e9fe8f72b1a924aa6b563ec1891108df9ec441

Observation b6ca2670-c379-4da0-9e7b-154b0e37e33e · outbound

This paper cites Language Models can Self-Lengthen to Generate Long Texts.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Language Models can Self-Lengthen to Generate Long Texts

Reference 54

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.596221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:85b460eb6e007a0c9169aa6f93a5076d4e66ab5ce51e88571a78faebdb24851f

Observation 94b0338d-1c4a-401d-a90a-92eac1743bbc · outbound

This paper cites Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier

Reference 55

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:13:13.587240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-05-20T11:09:22.027588Z digest=sha256:5dbe9b5deeb7e59ebb333d3aa2a9f3f9fe355096c847b48c52e9a9f89fcd72f7

Pith citing papers

No inbound Pith citation observations are available.