Pith. sign in

Paper Citation Record · LEDGER

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation

As of 20 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2505.13554.

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

pith.paper-citation-record.v1
2505.13554 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:33:13.008044Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

26 of 26 outbound references displayed

  • verified exact3
  • verified fuzzy0
  • unresolved23
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 89d63856-e34d-40af-b381-b64d8a295b73 · outbound

This paper cites online" 'onlinestring :=.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation online" 'onlinestring :=

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.897180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.897180Z digest=sha256:4373e158ea49c7a571014cecc89562d97ef8485916aea99a8c133fc46c5a8171

Observation ffb5e728-19cf-459d-bfa5-67ae8196edc0 · outbound

This paper cites write newline.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation write newline

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.902235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.902235Z digest=sha256:58fe108695672477a760b3503891f70d1ab92c57b975e53d59a5a8e9b7783fb1

Observation 18d1c06e-45f7-4063-8eca-56d1aa4d7395 · outbound

This paper cites Neural Machine Translation by Jointly Learning to Align and Translate.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Neural Machine Translation by Jointly Learning to Align and Translate

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.906520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.906520Z digest=sha256:6eed94d6ec4b2c529b49fa2020f878172d0dd006ddee4132370b475409a126a8

Observation 9c15caf3-2559-40f7-9fa5-21ab6f57dbbd · outbound

This paper cites Unsupervised Cross-lingual Representation Learning at Scale.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unsupervised Cross-lingual Representation Learning at Scale

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.912422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.912422Z digest=sha256:dad0fa1b1c247e9b6c0b0cdeed42c730d7755c2c9a87e2381a7f17e231bc3837

Observation c72a1327-105e-4e67-b504-1888494c68fa · outbound

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

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.916137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.916137Z digest=sha256:5bbc3e25d5a78c32da574b75acb38baab384783f9ab0d7b568b44efd961b8508

Observation 04d00252-cb69-4ac8-9b46-b9fb9148568e · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.919809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.919809Z digest=sha256:a35c8c860c6e4b0cb49c2a0c8f1d360f4b616fb7c3c75bb92c8c0ea03a6e1c2c

Observation 88fbdf50-7e02-4865-b528-75704095876d · outbound

This paper cites Unsupervised Quality Estimation for Neural Machine Translation.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unsupervised Quality Estimation for Neural Machine Translation

Reference 7

Resolution
verified exact
local_arxiv, observed 2026-08-15T20:33:13.239745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-15T20:33:12.923905Z digest=sha256:64c661022dc2261d2d66e858311a2b411e6bf690775bd3248f646a68074ff919

Observation 20049e76-c664-4e69-b377-c5810fe0edfa · outbound

This paper cites How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.928616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.928616Z digest=sha256:8c169a716cac8da1c9701a7d8173603685c63f7b17d2aa9232948c2c7a4e6732

Observation 299d4070-90db-425d-b6a0-0a13c12a81e0 · outbound

This paper cites Adaptive Machine Translation with Large Language Models.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Adaptive Machine Translation with Large Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.933554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.933554Z digest=sha256:83b8cc12b078a1534413ee732f69d8481803286176cb9a013050e86e7157a79a

Observation 3887c801-4da2-4ed3-8430-ef90d67732eb · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.938009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.938009Z digest=sha256:95b4dd2cffe746cdcbed5fb549d1bda5afe01fd00aa4d7316fe325c7ee4ef4f5

Observation 2014b8a1-07bc-42bd-90e4-50facb4859ca · outbound

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

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Training language models to follow instructions with human feedback

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.942049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.942049Z digest=sha256:ba4b9ef82afbeabe5a34b11c4ca1d9dbff923eff3e23c67adb82c1b472da7bdb

Observation 7a025b8b-6126-4c1a-87d2-570eac3d2e0b · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.946796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.946796Z digest=sha256:7257f1f55ce8ce8e962985f889523270018ce31c6467c3d76aefca69ff957195

Observation 463bdccd-7808-42a8-802c-ca1f67ab23c3 · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.951035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.951035Z digest=sha256:cc972daf9b0987655cefc125eff7822afd348fa6a597e3b3a3e96fc16c031168

Observation fa44ce71-8cdb-42c7-9612-d3dddd0cce34 · outbound

This paper cites CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.959769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.959769Z digest=sha256:abcae089c7ae7b731ce1c5ebf2bd9fc1ceac77e718b3899efc22043d2efde885

Observation 83635262-5e32-4a5e-a03e-8e829a63e766 · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.963777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.963777Z digest=sha256:cf8043aed6e0ca9f6ed3dc6950586f6764a549e24f892ff8320ce0522e0aad9b

Observation 8f8cec74-55cd-4c8c-a4fa-9657eeaafbce · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 17

Resolution
verified exact
doi, observed 2026-08-15T20:33:13.047844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-15T20:33:12.967663Z digest=sha256:fe6e055f2342e0e8fe35d20f711257e97f6a666853db614922d70d5ec7c08150

Observation c0aaec66-833b-4253-b551-198244ba8b7f · outbound

This paper cites Sequence to Sequence Learning with Neural Networks.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Sequence to Sequence Learning with Neural Networks

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.971775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.971775Z digest=sha256:72979438aac098bc37fa9fd1c6f8f2dead100b46f1b36be0563e1d1692bfd85f

Observation 33ed4a23-7f0a-41db-9c0a-dfb15734afb8 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation LLaMA: Open and Efficient Foundation Language Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.975902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.975902Z digest=sha256:8ab310fe5696c3c89ace8ceb0e6e2d6a7e4079ce90855546649779fae475ac6c

Observation fa1c4411-2731-490e-9eab-8895e7d8c7a6 · outbound

This paper cites Attention Is All You Need.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Attention Is All You Need

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.980099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.980099Z digest=sha256:6812dab15bf4049bde37f61c1c5483fb111316d10c1d5e317bd8e204014a1452

Observation 88493198-826f-479c-8876-edf891eee8f0 · outbound

This paper cites Learning Deep Transformer Models for Machine Translation.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Learning Deep Transformer Models for Machine Translation

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.984119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.984119Z digest=sha256:51c89a478d82dab825f7dc13cb3c0373c1d288d52f12148a87ef865f9c6f779e

Observation 37a50796-4c88-4cd4-b113-54e43a0d7d89 · outbound

This paper cites LightSeq2: Accelerated Training for Transformer-based Models on GPUs.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation LightSeq2: Accelerated Training for Transformer-based Models on GPUs

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.988266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.988266Z digest=sha256:01b206284a90704744d8cb383632bcc792b00d3ef00fa7f400d7c840cd70da45

Observation e928ae3e-f9dd-4862-bfde-1513b55a7fc1 · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-15T20:33:13.308025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-15T20:33:12.992502Z digest=sha256:059806d02b6633310d8a5f0a17af9d1b6d0642aa055e9e4d17c03f6c87d730d7

Observation d46da066-31c3-4751-ae83-13c6d2eaf560 · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-15T20:33:13.295510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-15T20:33:12.996259Z digest=sha256:f2e0757bc54ab60601e603fa7dc9ff4db9d8db4a7b4673b2dac74e5253f7ed04

Observation 8d5ff02e-d431-4fe5-b542-891a35aba946 · outbound

This paper cites an unresolved cited work.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:12.999979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:12.999979Z digest=sha256:de2fe3455ba69a4133b58c0a66c805740d6b2f5edc2ea0659567c31110531b33

Observation 3476cc39-6f01-4f8f-8bfe-df2c305ec10f · outbound

This paper cites Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding

Reference 26

Resolution
verified exact
local_arxiv, observed 2026-08-15T20:33:13.098688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=arxiv_source observed=2026-08-15T20:33:13.003755Z digest=sha256:7d234cd5ff29501edb77841b649b34c552b53f18d98df86bc85ae935d284dfcd

Observation 657d53f0-d419-42a9-b39f-c3edb819b865 · outbound

This paper cites Prompting Large Language Model for Machine Translation: A Case Study.

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Prompting Large Language Model for Machine Translation: A Case Study

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-15T20:33:13.008044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T20:33:13.008044Z digest=sha256:66acdb5d263055b6bab66ef7c725de25059f72aaba41ae2f7456c5548c367974

Pith citing papers

No inbound Pith citation observations are available.