Paper Citation Record · LEDGER

Context-Enhanced Contrastive Search for Improved LLM Text Generation

As of 17 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2504.21020.

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

pith.paper-citation-record.v1
2504.21020 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:19:39.722184Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-07T08:17:27.376586Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T10:01:29.034589Z

Reference resolution

29 of 29 outbound references displayed

verified exact2
verified fuzzy2
unresolved24
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d172fd8a-d9ef-4260-a081-0b286da96824 · outbound

This paper cites Language Models are Few-Shot Learners.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Language Models are Few-Shot Learners

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.622630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac3ed8ba-6791-4f0d-b8b8-3135eab3b052 · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

Context-Enhanced Contrastive Search for Improved LLM Text Generation PaLM: Scaling Language Modeling with Pathways

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.631866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56ca12e4-89eb-44a0-8415-2702301c158e · outbound

This paper cites A Thorough Examination of Decoding Methods in the Era of LLMs.

Context-Enhanced Contrastive Search for Improved LLM Text Generation A Thorough Examination of Decoding Methods in the Era of LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.635579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f8d0ae-97e8-4404-9c06-8aad077ed07f · outbound

This paper cites Contrastive Search Is What You Need For Neural Text Generation.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Contrastive Search Is What You Need For Neural Text Generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.639307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1a1ec28-7c72-41ac-a51f-bfa0733fccb2 · outbound

This paper cites Contrastive learning penalized cross-entropy with diversity contrastive search decoding for diagnostic report generation of reduced token repet ition,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Contrastive learning penalized cross-entropy with diversity contrastive search decoding for diagnostic report generation of reduced token repet ition,

Reference 6

Resolution: verified exact; doi, observed 2026-08-16T11:19:39.877413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6278c7b4-9e26-4a62-a15d-55677c1858ed · outbound

This paper cites Contrastive decoding: Open-ended text generation as optiization,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Contrastive decoding: Open-ended text generation as optiization,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.647104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ad6c6c8-a295-4d49-a59e-34bcb2f2eba4 · outbound

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

Context-Enhanced Contrastive Search for Improved LLM Text Generation LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.650025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22e45354-eecf-41aa-a754-cab5ab7995f6 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.653229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4176f79-ad7e-4c80-866b-7c531c2ac9f8 · outbound

This paper cites Decoding Speculative Decoding.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Decoding Speculative Decoding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.657316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b8aa4c9-6991-4635-883e-078ba2f5ab8e · outbound

This paper cites FocusLLM: Precise Understanding of Long Context by Dynamic Condensing.

Context-Enhanced Contrastive Search for Improved LLM Text Generation FocusLLM: Precise Understanding of Long Context by Dynamic Condensing

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.660664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49b76e98-067e-4da8-a2cb-16981ed4cdd8 · outbound

This paper cites Neural Text Generation with Unlikelihood Training.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Neural Text Generation with Unlikelihood Training

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.664378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c67ab3cf-a08f-4df1-b85a-92385f9caee4 · outbound

This paper cites Hot or cold? Adaptive temperature sampling for code generation with large language models,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Hot or cold? Adaptive temperature sampling for code generation with large language models,

Reference 13

Resolution: malformed identifier; no resolver link, observed 2026-08-16T11:19:39.667995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd553179-bb15-47fa-8118-919c1405ac35 · outbound

This paper cites Locally typical sampling,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Locally typical sampling,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.670821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9508cb99-a8bd-4aca-a143-a112173db4a4 · outbound

This paper cites Trusting your evidence: Allucinate less with context- aware decoding,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Trusting your evidence: Allucinate less with context- aware decoding,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.673866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c694e2ac-b681-4f64-9072-af14e2464250 · outbound

This paper cites Fast Inference from Transformers via Speculative Decoding.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Fast Inference from Transformers via Speculative Decoding

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.676763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b0c04b-0de3-4d64-a4cd-0e64ed9deb3c · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Accelerating Large Language Model Decoding with Speculative Sampling

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.680208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bda96a02-f082-44cd-bff2-8d87e66013f8 · outbound

This paper cites LongGenBench: Long-context Generation Benchmark.

Context-Enhanced Contrastive Search for Improved LLM Text Generation LongGenBench: Long-context Generation Benchmark

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.683366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4bd7d4f-f41d-4079-8b39-1add30a45a8e · outbound

This paper cites MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers.

Context-Enhanced Contrastive Search for Improved LLM Text Generation MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.686557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 738a333a-dca9-442b-a7b4-81205a08d5b7 · outbound

This paper cites Language models are unsupervised multitask learner s,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Language models are unsupervised multitask learner s,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:19:40.047165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ecc9f67d-1b6a-4449-b7d0-434d9e82497b · outbound

This paper cites GPT-Neo: Large scale autoregressive language modeling with mesh-tensorflow,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation GPT-Neo: Large scale autoregressive language modeling with mesh-tensorflow,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.693047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 134bc03b-47ff-478c-b4fc-f59421ce5e95 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Context-Enhanced Contrastive Search for Improved LLM Text Generation OPT: Open Pre-trained Transformer Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.695933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4cc7326-e55b-4fec-a3c2-e0d18fe77040 · outbound

This paper cites Don’t give me the details, just the summary! Topic-aware convolutional neural networks for extreme summarization,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Don’t give me the details, just the summary! Topic-aware convolutional neural networks for extreme summarization,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.699722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37c5b69e-fbe8-44f6-b639-193d84df1d11 · outbound

This paper cites ROUGE: A package for automatic evaluati on of summaries,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation ROUGE: A package for automatic evaluati on of summaries,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:19:40.037524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff7225cb-11af-45b0-85b2-8b505efe2cd6 · outbound

This paper cites BLEU: A method for automatic evaluation of machine translation,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation BLEU: A method for automatic evaluation of machine translation,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.706558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c996a31-4007-4ad7-ba43-c86afaeacc15 · outbound

This paper cites C OMET: A neural framework for MT evaluation,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation C OMET: A neural framework for MT evaluation,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.710004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c494858-dabd-4b4f-9518-ee5008c5fad6 · outbound

This paper cites B ERT: Pre- training of deep bidirectional transformers for lan guage understanding,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation B ERT: Pre- training of deep bidirectional transformers for lan guage understanding,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.712687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cd14572-7404-4f98-8afd-f57929cf3b37 · outbound

This paper cites Unsupervised cross-lingual representation learning at scale,.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Unsupervised cross-lingual representation learning at scale,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:19:39.715653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e942283-92ff-42d1-93b1-ca97208b3437 · outbound

This paper cites Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:19:39.751504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5d82b6e2-b0e7-4d26-a4bb-88147c05fadd · outbound

This paper cites an unresolved cited work.

Context-Enhanced Contrastive Search for Improved LLM Text Generation Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:19:40.028738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation d59795e8-e28f-4c31-8815-1b465d5a6d74 · inbound

From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks cites this paper.

From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks Context-Enhanced Contrastive Search for Improved LLM Text Generation

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:01:29.038234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.