Pith. sign in

Paper Citation Record · LEDGER

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

As of 16 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2412.03253.

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

pith.paper-citation-record.v1
2412.03253 v1

Coverage vector

measured 62 of 62 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T22:41:18.444887Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:30:56.562707Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T21:30:57.370850Z

Reference resolution

62 of 62 outbound references displayed

  • verified exact0
  • verified fuzzy11
  • unresolved48
  • parse uncertain3
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d4fcfe96-f2d7-4773-ae84-0c0e4b35d467 · outbound

This paper cites Learning to summarize with human feedback.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Learning to summarize with human feedback

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.336053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.336053Z digest=sha256:ce3bc2b1d2ff2d4e8a59c5d37986553a012dfc9b2b603bbce4eef3673a456839

Observation 780423a1-fd20-4ffb-ac45-7a1967580944 · outbound

This paper cites Acegpt, localizing large language models in arabic, 2024.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Acegpt, localizing large language models in arabic, 2024

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:22.894747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:16.385403Z digest=sha256:976599fd593067384c0adfab1183816b1815cf880775ab1cb4116c52908cf37a

Observation 287211c1-edd6-4edc-8d90-199cbdad0f13 · outbound

This paper cites Training language models to follow instructions with human feedback.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Training language models to follow instructions with human feedback

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.434749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.434749Z digest=sha256:8761d07567f985dd3b0350c4fecee78a58ee11630be07c06deff66c153d0f604

Observation 67a2410b-6080-48b4-a7fc-c4b4f33a61e7 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Finetuned Language Models Are Zero-Shot Learners

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.457997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.457997Z digest=sha256:f03256c5c5226666ed7185a137f3a23300853c2f7a7c9d801c021d80628389ec

Observation a0f492ce-83cd-4770-b9ff-e7897bdc692d · outbound

This paper cites Lima: Less is more for alignment.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Lima: Less is more for alignment

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.467179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.467179Z digest=sha256:a45c203ac857a4a90dce5a9651c37b5d0523e00b15ef543edafee1bc1009e0c7

Observation 18248cac-772c-4a86-89e1-688ec83c3a18 · outbound

This paper cites Reformatted Alignment.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Reformatted Alignment

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.476238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.476238Z digest=sha256:2961397a7033b0bb52bd176d5dbd76aebb753295dc3d10a951a2770f5b0ea370

Observation 84109a36-4e6b-49b7-b4cb-348fee6684b7 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.484024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.484024Z digest=sha256:f483447c1ce1363f4bca1fde17f9fa16485ed4673a34cd4b33efe930fffa736f

Observation 48853b1b-8c90-4f0e-a433-09e2adf41e9d · outbound

This paper cites Attention is all you need.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Attention is all you need

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.510521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.510521Z digest=sha256:cebcb36fb0b96f60d6ccb59ef73fe8161a8c0b6fc42e0289456527568bb1d4ad

Observation 53c0d10e-8673-4a7c-8c9c-d132fb8788a6 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.520941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.520941Z digest=sha256:659564b148b03570ada2eee77ace2d4abfb31e7dc5b3028c9857eeacfdcc3330

Observation 65ecf153-9e41-4475-94d3-8f2d5b9a4d41 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.530568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.530568Z digest=sha256:81351e272426ad1544f2f548b27ac815dda82faaf2b744318d4ad40acf804c02

Observation 46778eab-5ed7-4681-a873-635f6d359030 · outbound

This paper cites Hashimoto.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Hashimoto

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.542808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.542808Z digest=sha256:3c9d8be91a1504652227a098d09cf5f82526b0105c5436be550e9640a0e2ddba

Observation bbe2a39d-1070-4547-b869-85d4eb6ad6cc · outbound

This paper cites Rlaif: Scaling reinforcement learning from human feedback with ai feedback, 2023.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Rlaif: Scaling reinforcement learning from human feedback with ai feedback, 2023

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.574784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.574784Z digest=sha256:9bb0e6334e4b67ca1d27a7f256b63575fbbc5ca1ac0df8b38bd50aeae2f96a36

Observation 272b5568-a605-4c1d-beba-12883454d05f · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Aligning Large Language Models with Human: A Survey

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.599664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.599664Z digest=sha256:ba325c39999e8eeb16bb858e31621c5473943363034a59297522cb12401a7de8

Observation 4d7c3042-ce7c-41a2-887e-c04da6ebb9c0 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Direct preference optimization: Your language model is secretly a reward model

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.624141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.624141Z digest=sha256:e1047f32336c0edabb9845c1d246a2bf4e98db3e0e82b970b05b750e6eb97b7a

Observation fdeb5a6b-eb99-4869-8a5c-92a45024cf9b · outbound

This paper cites A study of practical deduplication.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs A study of practical deduplication

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.647135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.647135Z digest=sha256:2eafc73b59bff956837ddb08e2ba98701c8a7d8306a356eb7a67c57867e411b4

Observation 9bd87c3f-8595-4b44-8a5d-af3857699207 · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.674895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.674895Z digest=sha256:aece170b3b6cdc4b9115a0e50fc9a35e7712e1f20ba0418252b03691fa57ef3e

Observation e5a7949d-2e8d-45a0-891b-f52913efb766 · outbound

This paper cites PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.693382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.693382Z digest=sha256:2ca8776be51628b9f644f28d0d0a4c72ae0497185ef2c3016a51033288ae3272

Observation 322b0f8c-f7b8-4d33-ae70-9b33a70e34cd · outbound

This paper cites When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.754752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.754752Z digest=sha256:ddf022133c8b9bf09a4214dcc429ec41edf65e743f53d698c4b825317e174f7e

Observation 6f609631-ccf4-468d-8c9b-dcdee3df629f · outbound

This paper cites Llama 3 model card.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Llama 3 model card

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.782495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.782495Z digest=sha256:c5222d58e781b8fb5bc8d5a3a7dc372f89854fcbed3b45ec171360251ba89fac

Observation e09b43ff-2416-4fd9-a580-c45606f02c8a · outbound

This paper cites Arabic natural language processing: Challenges and solutions.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Arabic natural language processing: Challenges and solutions

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:22.665143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:16.815267Z digest=sha256:0ec97633186b2d8abf323d2fd141167ec096fc38629dff49aa7748b0bb22b67b

Observation 035c8103-3941-4491-b89d-45ecb828477f · outbound

This paper cites "arabicmmlu: Assessing massive multitask language understanding in arabic.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs "arabicmmlu: Assessing massive multitask language understanding in arabic

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:22.629977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:16.838549Z digest=sha256:b09ea9cf3fe69e377cfadc48c40768f3c72a2bcdf10ecb7ac7962df3fdbc3be3

Observation ae41c236-657a-48f0-ae57-ad8122861fab · outbound

This paper cites EXAMS: A multi-subject high school examinations dataset for cross-lingual and multilingual question answering.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs EXAMS: A multi-subject high school examinations dataset for cross-lingual and multilingual question answering

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:22.530308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:16.858504Z digest=sha256:27b8ef5126f9a57472c55c22978b0645e1b73ccf3417ac8e9315401f6cf11117

Observation fb3ac2af-c3b6-4820-969e-5d6ae0889f3b · outbound

This paper cites AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.871862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.871862Z digest=sha256:9832aef0ec71057a5c25007fbee5ae3f0a3962c28173c4bfc7c3ae64e3c814d5

Observation 2c444fcc-7eae-4be6-a34f-4b71af006b3a · outbound

This paper cites Qwen Technical Report.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Qwen Technical Report

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.883113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.883113Z digest=sha256:ca79318801e9ebb01eed4cfca7312f00c39b08f32639a88d5d3ad4e41bd9208b

Observation d4bb41ae-4fc2-420a-b7e1-0efea69d5089 · outbound

This paper cites Jais and jais- chat: Arabic-centric foundation and instruction-tuned open generative large language models, 2023.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Jais and jais- chat: Arabic-centric foundation and instruction-tuned open generative large language models, 2023

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:22.414760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:16.891313Z digest=sha256:e8767acda7d4927be53eac557f46e880dbaad04ff064cc7be1140caad238ca88

Observation eda54012-ac71-4c24-b49e-0c54ca12b6ec · outbound

This paper cites SlimPajama: A 627B token cleaned and deduplicated version of RedPajama.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs SlimPajama: A 627B token cleaned and deduplicated version of RedPajama

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.901062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.901062Z digest=sha256:924665e4a16661e64bbb9385910d385e697260312ee06702a69aaccc5e0c6875

Observation eb1ffae9-2875-408c-8fa6-a0ee2ce5619b · outbound

This paper cites Chinese tiny llm: Pretraining a chinese-centric large language model, 2024.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Chinese tiny llm: Pretraining a chinese-centric large language model, 2024

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:22.191822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:16.935409Z digest=sha256:07478e3e64bc8ace3b32596a46d328743bfaa46e697356aa3c6be08a43b7ae33

Observation ad3ba5bc-c6fa-431c-a46d-3f324ddb501a · outbound

This paper cites Wikimedia downloads.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Wikimedia downloads

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:16.966777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:16.966777Z digest=sha256:a87e58795ac3fabbc195d2c846636d5d5c2fdb065ee2645c6382f26d53e70537

Observation 90bf52a3-0198-441e-821b-a62d5754e39b · outbound

This paper cites Jiang, Jia Deng, Stella Biderman, and Sean Welleck.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Jiang, Jia Deng, Stella Biderman, and Sean Welleck

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.020213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.020213Z digest=sha256:364fcc4901c16fe2a68c032ad75c314461dc64c6ed2cb006ec17b2b1eff31772

Observation 7054f4c6-32f3-439b-a76e-975448e9e2af · outbound

This paper cites Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, and Jinchao Xu.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, and Jinchao Xu

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.104941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.104941Z digest=sha256:025db12eafb0162b14bf1f8928c9cc9e047d2e938eec48377c5625f87af4f44b

Observation c9f314dc-007d-44b4-a7f3-ce430c7e7685 · outbound

This paper cites Opencompass: A universal evaluation platform for foundation models.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Opencompass: A universal evaluation platform for foundation models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.165123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.165123Z digest=sha256:3fff86f0db125a4c33e8ad2bf9de4e5bee22d39040c58e4b93c93e286093dc0b

Observation 20c2ae4f-a03d-4de1-be23-63ba8c07e2cd · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.201915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.201915Z digest=sha256:f664731e763852d9f24a97c3c7e2537ea91d4887df6614296670c20674e8af92

Observation ed9c92a2-737c-44fe-9a4c-e5c72058eaad · outbound

This paper cites Large Language Models are not Fair Evaluators.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Large Language Models are not Fair Evaluators

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.259546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.259546Z digest=sha256:3a8483b2a722e96c480bf21bdd4b93bce8ec0e78397588ed64551867119d716b

Observation f864a6fa-d962-4f3e-9dcd-d0b0151d779f · outbound

This paper cites The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.292783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.292783Z digest=sha256:a4e60634bcefe115760c4ececee27be7360ad6a5a7af7cbec1f818ea1dd527dc

Observation 6f003954-aa35-4eb1-99b8-0acc88be5a45 · outbound

This paper cites Textbooks Are All You Need.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Textbooks Are All You Need

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.331131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.331131Z digest=sha256:3a82cc56d7486c47f1644514f6b2270dd944252e92e763e96908621ede6d96fa

Observation 01ae4bbc-daa9-4e78-9e35-fcd22d04d4a5 · outbound

This paper cites Textbooks Are All You Need II: phi-1.5 technical report.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Textbooks Are All You Need II: phi-1.5 technical report

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.353363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.353363Z digest=sha256:5d34c479436506e3b2e7967d3775a4ccf78deb2cd8f6252f4b760a80dbe19600

Observation 4d3361bb-7ed3-4daf-9ef9-29348d1d9641 · outbound

This paper cites Phi-2: The surprising power of small language models.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Phi-2: The surprising power of small language models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.381487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.381487Z digest=sha256:5e15e485da0f97333304dfbed673cfd608f95390c9cc36e949d3fce0260a6f13

Observation 478962b9-6511-452d-8d23-7be35ae18bc8 · outbound

This paper cites Quality at a glance: An audit of web-crawled multilingual datasets.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Quality at a glance: An audit of web-crawled multilingual datasets

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:21.784730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.424562Z digest=sha256:624beb356fe5d19f3cd1301ae335de9097283778de96bbb929826d6dd0158505

Observation 9ffb7686-a2bd-458c-bdb3-12e24d32dfa9 · outbound

This paper cites Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.466195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.466195Z digest=sha256:d00ef0a78f200865bce476a046ead729b16a92624063f0fa2193203eae4c1547

Observation 3223159f-64da-4da2-877f-d7f6438de931 · outbound

This paper cites Preprocessing arabic text on social media.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Preprocessing arabic text on social media

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:21.668735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.503229Z digest=sha256:4ef740efe8f7eea7adc2d2462efdc2a5ddbf5c846c528d699ebd82ce0816ffd1

Observation f894d4c1-6c47-4509-8cd5-9efff08edf49 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.551449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.551449Z digest=sha256:66c319fe0b46a419c96e8c0f3c24d2b9afb030304a9a655120b807707c11a351

Observation d5af562e-77c8-4ea8-b3c2-534c46e802fc · outbound

This paper cites CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.596836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.596836Z digest=sha256:2cd1aaa5d44129b20d2ab1dc1603171797b314e0b0203a015acb1da929c70822

Observation 12ead447-8dcb-42ec-839e-2618ab6a0882 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Constitutional AI: Harmlessness from AI Feedback

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.677226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.677226Z digest=sha256:4f69409ccade914aa506e88e83d80b6945e3ac48bada80ee8e85136c23956be1

Observation 07df9e27-759c-4048-be3c-26ded23721f2 · outbound

This paper cites Aligner: Efficient Alignment by Learning to Correct.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Aligner: Efficient Alignment by Learning to Correct

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.718726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.718726Z digest=sha256:80435ffebb35b8b1d7a0fac77265eb4d77039d61b7278f3ed67f498317d17d11

Observation 195e61ae-67b5-4609-ac52-649fe2dc0bd3 · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Llamafactory: Unified efficient fine-tuning of 100+ language models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-11T22:41:17.772248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:17.772248Z digest=sha256:8fbc0c6301e3f80ec7548acef9a224572ebc1512e318e394850616c9ad100c7c

Observation 811bc234-d5a3-4195-8198-a3db54964f74 · outbound

This paper cites Measuring massive multitask language understanding.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Measuring massive multitask language understanding

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:21.516847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.791126Z digest=sha256:9923cdc702ff564e750ef5a88a67a14dfc5b1f00ccf65952fe4ef1508afb4d1b

Observation 5c1b27b9-22e1-410c-ace3-ad2b7048d7a8 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 47

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:21.318285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.840532Z digest=sha256:386477ecce2be3a4fab9ae3d79c559aca6790921eac95b23d997a5d6713fdf76

Observation 9b624a10-9385-4d04-a7ba-ef9816a0a7d5 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:21.194857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.867547Z digest=sha256:2913d5e48c5e1a66785c51b1fd238cc3128aee45aba17e757bc72feb2719a3fe

Observation 3f636cec-be43-4a9b-b744-a1f1690a2f03 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 49

Resolution
parse uncertain
raw_fallback, observed 2026-08-11T22:41:21.064807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.912949Z digest=sha256:bfb4268bbb5b4bc7451a69539c433b2d1af7a71769af79a0e51d4ecf6995f4ad

Observation 46aa44ef-0751-41d3-ad1f-b8c9e7c10b34 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 50

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:21.004738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:17.950361Z digest=sha256:2514680163433fa40944f9984e3dd67f15f48f574df77a599c181493c859aa76

Observation 4bb14ce0-2f80-41d3-8f69-78003686697b · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 51

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.896973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.005230Z digest=sha256:b898c6d27c6a2a238544989d7557380870683f92527d804ee9772d1eb39899b2

Observation 1cd762a5-2912-4018-958c-98c15a7d8daa · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 52

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.779644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.054745Z digest=sha256:5e9b66020576107180cfbfa6771d04fcf03e9bbc2c174ae896ec7655c2e8f977

Observation dc5be2df-fcd5-426c-bc03-f4d9ef503281 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 53

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.679651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.095158Z digest=sha256:4ed45a95d637db865be824b56be7bbfb0b179b8c066798364aec8af34ee46d19

Observation ebda2b06-36b9-49fa-9ce7-1daa496d76d7 · outbound

This paper cites for example: ### Arabic text data rewriting Arabic text: á ‚j JË éJ ËAÓ XP@ñ Ó © Ôg.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs for example: ### Arabic text data rewriting Arabic text: á ‚j JË éJ ËAÓ XP@ñ Ó © Ôg

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:20.566343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.143632Z digest=sha256:5704441dbc10a596f5e5bc6e5e3a831ab56099ced300d125532379f3516b34c5

Observation 58e573ee-fa3c-4c45-b153-0483ebfd7767 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 55

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.444788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.194824Z digest=sha256:b89fdb8db1accbf22d5bbe1d2d4c2825f9f3457948c3e145c5138d423923d490

Observation a0e068e7-5aca-49e7-ad25-35ede5682b6a · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 56

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.348391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.246539Z digest=sha256:2bd8f852dd3a50758dd8e9d5405400e8a35a2db340afb5be1df358fd415923a6

Observation fd2af012-8e90-4ba3-b53f-38df13105d35 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 57

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.282848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.279285Z digest=sha256:0d9aa179053c971f4adcb9e93bb4c2386738ba37f2bc271f5472fd6aecab8fd9

Observation 9a82d610-e926-4dca-a300-bf15e18ed3c4 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 58

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:20.188812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.287882Z digest=sha256:e8b84701e41e051405e11a40412a552b1d00bcd738de0c3a0269374ce375ffb4

Observation c40fd97f-9cd7-449d-9bd4-64c101bddbac · outbound

This paper cites The variance and average of these experiments are reported as ‘random (x3)’.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs The variance and average of these experiments are reported as ‘random (x3)’

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T22:41:20.116115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.309438Z digest=sha256:b9b5d3d74fe79516bdf50f7fb0973d62b9beff34e13b3f3108fcfbee35098dfe

Observation f3924b62-113b-477c-a621-81e1b24a1cb8 · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 60

Resolution
parse uncertain
no resolver link, observed 2026-08-11T22:41:18.338439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T22:41:18.338439Z digest=sha256:70b0c3f3a3eeaf60692ae7ac59ff460356a73b4e54c15597c74e0ea8f1414705

Observation 7ce123e2-ef33-409e-8914-957aeb26beef · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 61

Resolution
parse uncertain
raw_fallback, observed 2026-08-11T22:41:20.004825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.394003Z digest=sha256:62111192f6ac88afffe9175e0ac9d27e2d5e236a582550eb0656c4be755d249b

Observation 5254a99b-733d-45e6-a3de-23f32313c46b · outbound

This paper cites an unresolved cited work.

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs Unresolved cited work

Reference 62

Resolution
unresolved
raw_fallback, observed 2026-08-11T22:41:19.851771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T22:41:18.444887Z digest=sha256:5ae39d0274f86ed9f8fed9e67a8aff236e4e94b4f4033623d5d2da78661bfa68

Pith citing papers

Observation 074f58ac-0044-438b-8488-0d311c603f78 · inbound

On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena cites this paper.

On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Reference 34

Resolution
verified exact
local_arxiv, observed 2026-08-10T21:30:57.375574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-10T21:30:56.562707Z digest=sha256:8f4f2e1dcbdca8ad0bf6b996c60ffe63be3b1b311e5082162937a06a8d5e58c4