Paper Citation Record · LEDGER

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean

As of 10 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2506.01237.

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

pith.paper-citation-record.v1
2506.01237 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:52:27.102294Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

30 of 30 outbound references displayed

verified exact0
verified fuzzy23
unresolved2
parse uncertain0
malformed identifier5
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f0316d5-ae1a-4f30-869e-e41bb2a62d79 · outbound

This paper cites It en- hances the connection of knowledge between Korean and English.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It en- hances the connection of knowledge between Korean and English

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.730460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4fbe011-facb-4ee0-99dd-25166b86b62f · outbound

This paper cites It is trained by utilizing instruction fine-tuning methods, including su- pervised fine-tuning (SFT) and direct pref- erence optimization (DPO) (Rafailov et al., 2023).

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It is trained by utilizing instruction fine-tuning methods, including su- pervised fine-tuning (SFT) and direct pref- erence optimization (DPO) (Rafailov et al., 2023)

Reference 2

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:52:27.723264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c812159d-e95b-46b6-981d-bed8c6b667ea · outbound

This paper cites This model is trained using the data, such as Peng et al.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean This model is trained using the data, such as Peng et al

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:52:27.715527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f6d9de8-2242-49f1-b406-a8412967b2e5 · outbound

This paper cites Specifically, this model is trained by utilizing DPO.8.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean Specifically, this model is trained by utilizing DPO.8

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:52:27.708136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 518ea0b2-6e91-46cc-bc74-a466d4c6a52c · outbound

This paper cites This model is trained to utilize the system prompt.9.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean This model is trained to utilize the system prompt.9

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.699090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8479455c-00a3-433e-b1c0-e2e6f97e257a · outbound

This paper cites 7https://huggingface.co/yanolja/ EEVE-Korean-10.8B-v1.0 8https://github.com/axolotl-ai-cloud/ axolotl 9https://huggingface.co/LGAI-EXAONE/ EXAONE-3.5-7.8B-Instruct.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean 7https://huggingface.co/yanolja/ EEVE-Korean-10.8B-v1.0 8https://github.com/axolotl-ai-cloud/ axolotl 9https://huggingface.co/LGAI-EXAONE/ EXAONE-3.5-7.8B-Instruct

Reference 6

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:52:27.689699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 051974d3-4825-47bb-9768-a22ea594bd1e · outbound

This paper cites an unresolved cited work.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:52:27.679639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 168d8a11-122d-4271-9d8d-79a1ef3631c0 · outbound

This paper cites • English-centric LLMs.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean • English-centric LLMs

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.671608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4095267a-bd6a-4cb6-9048-c97d9402afe2 · outbound

This paper cites It has been instruction-tuned to enhance its performance in various natural language understanding and generation tasks.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It has been instruction-tuned to enhance its performance in various natural language understanding and generation tasks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.500318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4a64fad-c225-4583-8b65-914b827f0f53 · outbound

This paper cites It has been pre-trained on approximately 15 trillion tokens from publicly available sources.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It has been pre-trained on approximately 15 trillion tokens from publicly available sources

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.427842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 47328389-96c7-4866-ab9e-491ccb661216 · outbound

This paper cites It demonstrates superior performance in general knowledge and reasoning tasks, achieving high scores on benchmarks such as MMLU-Pro and MMLU- redux.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It demonstrates superior performance in general knowledge and reasoning tasks, achieving high scores on benchmarks such as MMLU-Pro and MMLU- redux

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.360007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 85b91125-aa42-4fd5-87c1-53a1bd672ee1 · outbound

This paper cites It is a text-to-text, decoder-only large language model, with open weights for both pre-trained and instruction-tuned vari- ants.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It is a text-to-text, decoder-only large language model, with open weights for both pre-trained and instruction-tuned vari- ants

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.664304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7418b453-a3cd-454e-bcd5-d6ef8f578d43 · outbound

This paper cites It is de- signed to deliver high performance across var- ious natural language processing tasks, bene- fiting from its extensive parameter count and advanced training methodologies.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It is de- signed to deliver high performance across var- ious natural language processing tasks, bene- fiting from its extensive parameter count and advanced training methodologies

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.656851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c98ca859-b053-451f-816d-de4da0096b49 · outbound

This paper cites It is designed to handle various nat- ural language understanding and generation tasks, supporting multiple languages, includ- ing English and Chinese.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It is designed to handle various nat- ural language understanding and generation tasks, supporting multiple languages, includ- ing English and Chinese

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.647836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 04c0b046-ae23-4dec-9e32-89630f5abdd0 · outbound

This paper cites It offers enhanced performance in lan- guage understanding and generation tasks, with support for multiple languages and a con- text length of up to 128,000 tokens.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It offers enhanced performance in lan- guage understanding and generation tasks, with support for multiple languages and a con- text length of up to 128,000 tokens

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.640040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 800f19c3-7416-43bf-bd88-f70be22a9ea8 · outbound

This paper cites It sup- ports a context length of up to 128,000 to- kens and is designed to handle complex tasks across multiple languages, including English and Chinese.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It sup- ports a context length of up to 128,000 to- kens and is designed to handle complex tasks across multiple languages, including English and Chinese

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.632240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 09094eab-8992-4983-8325-a1867a8cc242 · outbound

This paper cites It has been fine-tuned using reasoning data generated by DeepSeek-R1, resulting in enhanced performance in reasoning tasks.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It has been fine-tuned using reasoning data generated by DeepSeek-R1, resulting in enhanced performance in reasoning tasks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.623776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 59fabfb4-b184-42fd-a180-dd4aef9fb392 · outbound

This paper cites It has been fine- tuned with reasoning data from DeepSeek-R1, achieving state-of-the-art results in various benchmarks.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It has been fine- tuned with reasoning data from DeepSeek-R1, achieving state-of-the-art results in various benchmarks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.615741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4b8f039f-1511-4e09-81c5-8e60edabc237 · outbound

This paper cites budget forcing.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean budget forcing

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.561205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9fe0ef9f-69e3-4443-8611-ccc82dc63ae1 · outbound

This paper cites It is designed for real-time interactions and has been integrated into various Google prod- ucts, including Bard and Pixel smartphones.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It is designed for real-time interactions and has been integrated into various Google prod- ucts, including Bard and Pixel smartphones

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.340272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 38240ac7-0be4-4170-8aa5-efc88dfaaa20 · outbound

This paper cites It introduces fea- tures such as a Multimodal Live API for real- time audio and video interactions, enhanced spatial understanding, and integrated tool use, including Google Search.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It introduces fea- tures such as a Multimodal Live API for real- time audio and video interactions, enhanced spatial understanding, and integrated tool use, including Google Search

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.324463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1de16268-a40c-4b2c-a3c9-9076e88de300 · outbound

This paper cites It features a context window of up to 200,000 tokens, allowing it to process extensive text sequences effectively.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It features a context window of up to 200,000 tokens, allowing it to process extensive text sequences effectively

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.309300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b4953cd-dcdb-45c9-b83b-c27fb5feed45 · outbound

This paper cites It maintains a large context window and has been fine-tuned for better alignment with hu- man preferences.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It maintains a large context window and has been fine-tuned for better alignment with hu- man preferences

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.296196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0b144209-f3ef-40e4-9f9e-0e64933b5e0c · outbound

This paper cites It has been widely used in applications requiring natural language understanding and generation.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It has been widely used in applications requiring natural language understanding and generation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.280688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7dc489f5-39c2-4c42-ba18-830aaa88d5ef · outbound

This paper cites It offers rapid response times and has been integrated into various applications for real-time interactions.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It offers rapid response times and has been integrated into various applications for real-time interactions

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.258217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 48ef840a-2471-4799-a338-842f4de48ef2 · outbound

This paper cites It ex- hibits rapid response times comparable to hu- man reactions and has enhanced performance in non-English languages.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean It ex- hibits rapid response times comparable to hu- man reactions and has enhanced performance in non-English languages

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.243231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 13635027-7000-4c17-a852-4bcea4e4b444 · outbound

This paper cites think- ing.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean think- ing

Reference 30

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:52:27.226564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e1985cb-ce9c-4add-8f49-8ba247f9b960 · outbound

This paper cites In Proceedings of the 58th Annual Meet- ing of the Association for Computational Linguistics , pages 4609–4622, Online.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean In Proceedings of the 58th Annual Meet- ing of the Association for Computational Linguistics , pages 4609–4622, Online

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.747529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a52da19e-6583-4709-9fa5-683c456159db · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T11:52:26.406804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b35ffa67-b76c-471a-ac2b-53c49fff9a1e · outbound

This paper cites In Findings of the As- sociation for Computational Linguistics: ACL 2024 , pages 12159–12173, Bangkok, Thailand.

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean In Findings of the As- sociation for Computational Linguistics: ACL 2024 , pages 12159–12173, Bangkok, Thailand

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:52:27.739596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

No inbound Pith citation observations are available.