Paper Citation Record · LEDGER

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding

As of 16 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2509.07676.

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

pith.paper-citation-record.v1
2509.07676 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:19:09.743494Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

31 of 31 outbound references displayed

verified exact0
verified fuzzy13
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57118733-1423-4356-9473-41440fa7d448 · outbound

This paper cites GPT-4 Technical Report.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.422657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f373c84c-14c5-4c47-93c4-1175f13f53c3 · outbound

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

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.429682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 044952b8-95cd-46a2-94a7-093110ad1801 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.439040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1413df1-6f29-4801-b672-03ff4cb6aac5 · outbound

This paper cites LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.448240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84b4a722-0359-4956-aaff-1b36163bb59b · outbound

This paper cites Exploring and evaluating hallucinations in llm-powered code generation.arXiv preprint arXiv:2404.00971, 2024.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Exploring and evaluating hallucinations in llm-powered code generation.arXiv preprint arXiv:2404.00971, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.453349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e627e9c-e08c-4f46-b378-457ea67d0cc3 · outbound

This paper cites Towards mitigating LLM hallucina- tion via self reflection.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Towards mitigating LLM hallucina- tion via self reflection

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:11.218648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0f6b47f4-fe1a-4504-ba35-1fb613feba99 · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.Advances in Neural Information Processing Systems, 2024.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Self-refine: Iterative refinement with self-feedback.Advances in Neural Information Processing Systems, 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:11.194195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 270f8c03-8f9c-4d5b-8917-84e811980007 · outbound

This paper cites Language models can solve computer tasks.Advances in Neural Information Processing Systems, 2024.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Language models can solve computer tasks.Advances in Neural Information Processing Systems, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:11.167282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2d3b17a6-6a4e-46a2-a8fb-09a5b27289e0 · outbound

This paper cites Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.493208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1480cd7e-847d-451c-8e7e-7188269ecf36 · outbound

This paper cites Iterative translation refinement with large language models.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Iterative translation refinement with large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:11.146632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d3d9830c-fa49-4841-8d3f-7bcfca04b1f7 · outbound

This paper cites Large language models cannot self-correct reasoning yet.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Large language models cannot self-correct reasoning yet

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:11.117414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 65ee5cd1-671c-4f7d-9038-4fd3ddc14dec · outbound

This paper cites Perplexity—a measure of the difficulty of speech recognition tasks.The Journal of the Acoustical Society of America, 62(S1):S63–S63, 1977.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Perplexity—a measure of the difficulty of speech recognition tasks.The Journal of the Acoustical Society of America, 62(S1):S63–S63, 1977

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.524884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdf0e12-6751-40e3-bff6-4e9ab3347e12 · outbound

This paper cites an unresolved cited work.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:19:11.054165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 60a07271-3a9a-433a-848b-0a3e2033bb65 · outbound

This paper cites Take care of your prompt bias! investigating and mitigating prompt bias in factual knowledge extraction.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Take care of your prompt bias! investigating and mitigating prompt bias in factual knowledge extraction

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:11.005582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fbd401b5-4518-487e-a6f5-0884ef04392a · outbound

This paper cites Self-Reflection Makes Large Language Models Safer, Less Biased, and Ideologically Neutral.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Self-Reflection Makes Large Language Models Safer, Less Biased, and Ideologically Neutral

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.555762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e3eb9f-37be-40b1-8b90-64b40b2a1128 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Training Verifiers to Solve Math Word Problems

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.566216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f7133e5-fbb6-44bb-813c-917f5be8a6cd · outbound

This paper cites Solving general arithmetic word problems.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Solving general arithmetic word problems

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.949345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1eeae337-f493-4e10-a5ff-8ac02c415909 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Evaluating Large Language Models Trained on Code

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.582635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da0eeae7-f72f-4435-a5e5-b7652d1c37cf · outbound

This paper cites INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.592775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9362c561-edd2-42a9-8205-98c98d39e8d5 · outbound

This paper cites The Llama 3 Herd of Models.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding The Llama 3 Herd of Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.606648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 830c5b28-362d-431f-aae3-29116a44c621 · outbound

This paper cites Qwen2.5 Technical Report.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Qwen2.5 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.623115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50b90ba-6502-49f0-b9f5-a7d31f485883 · outbound

This paper cites The curious case of neural text degeneration.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding The curious case of neural text degeneration

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.881186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9a881f3c-a9a0-4a34-a845-21b52dea46b0 · outbound

This paper cites GPT-4o System Card.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding GPT-4o System Card

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.639967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6190418-edf5-45ac-bae9-69e1c9fe1656 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Measuring mathematical problem solving with the MATH dataset

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.849459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e7e6fabe-8bbc-41d6-9c57-9b9a48a3e194 · outbound

This paper cites Human or LLM? A Comparative Study on Accessible Code Generation Capability.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Human or LLM? A Comparative Study on Accessible Code Generation Capability

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.670071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e12f11-27fc-4ed6-8c48-f9e2a15bde4f · outbound

This paper cites an unresolved cited work.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:19:10.777991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b51f894a-2602-4dff-b274-3dbd802afaf2 · outbound

This paper cites Learning to write with cooperative discriminators.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Learning to write with cooperative discriminators

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.728576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f62bdd22-db34-497e-85d8-e0bd33502732 · outbound

This paper cites Varshney.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Varshney

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.683742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7ae12652-a1be-4d1e-9e86-b69c4dadc0f5 · outbound

This paper cites Improving open-ended text generation via adaptive decoding.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Improving open-ended text generation via adaptive decoding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.656099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 30dd9627-fbc0-40c8-b180-0188d8b1db00 · outbound

This paper cites Chain-of-thought reasoning without prompting.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Chain-of-thought reasoning without prompting

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:10.619115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3cb74c30-02bd-460b-9282-8d2509debee2 · outbound

This paper cites Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning.

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:09.743494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.