Paper Citation Record · LEDGER

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

As of 14 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 3 inbound Pith citation observations for arXiv:2412.11556.

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

pith.paper-citation-record.v1
2412.11556 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T14:53:05.993724Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:18:21.906109Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T13:01:23.426021Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy11
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 108ed56d-534e-4a5b-a79b-cffcb8617ea3 · outbound

This paper cites an unresolved cited work.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-11T14:53:06.257920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation efcb2972-75fc-4a61-8ab9-f4f24c324847 · outbound

This paper cites The Llama 3 Herd of Models.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.917628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4989ea08-aa33-4dd0-bdad-99ca2c21efd4 · outbound

This paper cites an unresolved cited work.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-11T14:53:06.316743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 40c01b9e-e723-4523-b7d8-0fb927a882cf · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.935530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7758a319-e8c4-4002-ab26-a09df6f5922b · outbound

This paper cites Meta-Task Prompting Elicits Embeddings from Large Language Models.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Meta-Task Prompting Elicits Embeddings from Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.939461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc4cf6c-2208-4cb9-a08e-a228e0a7aca1 · outbound

This paper cites AnglE-optimized Text Embeddings.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs AnglE-optimized Text Embeddings

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.943734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64afa96f-68a7-4d35-8637-7117b79dd4e5 · outbound

This paper cites Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.947792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 540d13bb-0eae-430f-9666-8e04dd8daa98 · outbound

This paper cites In Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014 , pages 216–223.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014 , pages 216–223

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.294130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 62d74e90-e4b5-4092-ace0-fc3dfcaad84c · outbound

This paper cites Generative Representational Instruction Tuning.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Generative Representational Instruction Tuning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.955495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7ef034-ef87-4e85-88e6-17d2f871fe21 · outbound

This paper cites MTEB: Massive Text Embedding Benchmark.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs MTEB: Massive Text Embedding Benchmark

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.959574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7d8345a-23cf-4941-a151-cb1036ec8e1a · outbound

This paper cites In Proceedings of the 2013 conference on empiri- cal methods in natural language processing , pages 1631–1642.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 2013 conference on empiri- cal methods in natural language processing , pages 1631–1642

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.282271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4f665b67-7b9d-4602-9ae0-3b424173a7cc · outbound

This paper cites Repetition Improves Language Model Embeddings.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Repetition Improves Language Model Embeddings

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.967185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fafe3187-d9b1-452d-a196-2de4d501bd2d · outbound

This paper cites In Findings of the Association for Com- putational Linguistics: ACL 2023 , pages 1102–1121.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Findings of the Association for Com- putational Linguistics: ACL 2023 , pages 1102–1121

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.270139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 77d8d5f5-340f-45de-a660-fb2aeb91634b · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Gemma 2: Improving Open Language Models at a Practical Size

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.974806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67bd6a3b-6023-499d-9885-1c0dacd754e1 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.978674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c987c767-1e0f-4b53-b7d9-ace33d12b5e1 · outbound

This paper cites Qwen2 Technical Report.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Qwen2 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.982600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 690fb787-8cbe-455d-95d4-5252b8001553 · outbound

This paper cites Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.986519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0fe18a-0312-428f-9941-e91045cc824e · outbound

This paper cites The representative word for sentence <PST> ’[TEXT]’ is:.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs The representative word for sentence <PST> ’[TEXT]’ is:

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.245512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 71d7c8b5-7ee0-4092-af7e-e0f6007e54ed · outbound

This paper cites In Proceedings of the 6th International Workshop on Semantic Evalua- tion, SemEval@NAACL-HLT 2012, pages 385–393.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 6th International Workshop on Semantic Evalua- tion, SemEval@NAACL-HLT 2012, pages 385–393

Reference 2012

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.345641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e8e9d304-a31b-44d4-948d-2c62b752d486 · outbound

This paper cites In Proceed- ings of the Second Joint Conference on Lexical and Computational Semantics, *SEM 2013 , pages 32–43.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceed- ings of the Second Joint Conference on Lexical and Computational Semantics, *SEM 2013 , pages 32–43

Reference 2013

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.336084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7de734b9-e67d-4251-903a-08a550f460a4 · outbound

This paper cites In Proceedings of the 8th International Workshop on Semantic Evaluation, SemEval@COLING 2014, pages 81–91.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 8th International Workshop on Semantic Evaluation, SemEval@COLING 2014, pages 81–91

Reference 2014

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.364693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e4d5623f-ee44-4e7b-a43b-535780dac4e1 · outbound

This paper cites In Proceedings of the 9th International Work- shop on Semantic Evaluation, SemEval@NAACL- HLT 2015, pages 252–263.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 9th International Work- shop on Semantic Evaluation, SemEval@NAACL- HLT 2015, pages 252–263

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.374074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4e9f45d5-a87a-48e3-9689-0c92f5614879 · outbound

This paper cites In Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2016, pages 497–511.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2016, pages 497–511

Reference 2016

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.355275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5e3cf048-dc15-4c8f-8ad3-1b4beb8b8923 · outbound

This paper cites SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.907487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ddd876-1993-4469-9f85-06a84649374f · outbound

This paper cites In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, pages 4171–4186.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, pages 4171–4186

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.326899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4bc6f53d-b46a-433b-8d40-9a6fb43ce96d · outbound

This paper cites Language Models are Few-Shot Learners.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Language Models are Few-Shot Learners

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.903623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d57fae1-cb7f-4915-87e4-3ab781e86955 · outbound

This paper cites In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages 6894–6910.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages 6894–6910

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:53:06.305665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 587812f3-9419-4d4f-a230-7593322c6bcb · outbound

This paper cites Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.931474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c45e951-6ada-45e9-9556-78831fd5d4b1 · outbound

This paper cites Scaling Sentence Embeddings with Large Language Models.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Scaling Sentence Embeddings with Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.927197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bde0649-a4d5-4a59-b05e-7530f3345833 · outbound

This paper cites LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T14:53:05.899934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 583693af-66e4-4723-9206-1fad1f4e1218 · outbound

This paper cites Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering.

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering

Reference 2025

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T14:53:06.196207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation b724c061-ebe8-466a-8f05-66db570e912c · inbound

Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning cites this paper.

Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:21.906109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a8f6853-ed34-488e-91bc-60165a83da4d · inbound

FreeRet: MLLMs as Training-Free Retrievers cites this paper.

FreeRet: MLLMs as Training-Free Retrievers Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:01:23.429112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 255c323b-f667-4d5a-9ada-2c6cf0d17b70 · inbound

FreeRet: MLLMs as Training-Free Retrievers cites this paper.

FreeRet: MLLMs as Training-Free Retrievers Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.359594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.