Paper Citation Record · LEDGER

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking

As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2509.06472.

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

pith.paper-citation-record.v1
2509.06472 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:34:31.452743Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

40 of 40 outbound references displayed

verified exact4
verified fuzzy6
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 34402aee-e5a5-4af7-afd6-1ebd45bb45c2 · outbound

This paper cites A Survey of Large Language Models.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking A Survey of Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:27.996898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89206a27-b02e-410e-ac4e-32de794e9e75 · outbound

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

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:28.108578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e335536-f9fd-4aaa-9f41-fd8666150f50 · outbound

This paper cites Qwen2.5-Coder Technical Report.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Qwen2.5-Coder Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:28.259462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2231b0-ee88-477b-acb4-4e569b592af4 · outbound

This paper cites To- wards mitigating llm hallucination via self reflection.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking To- wards mitigating llm hallucination via self reflection

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:32.527372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e2afd3e3-d344-421b-8b66-6b143d16d886 · outbound

This paper cites Knowledge injection to counter large language model (llm) hallucination.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Knowledge injection to counter large language model (llm) hallucination

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:32.516375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 278eea70-670e-41cc-ae50-0a94dc11438e · outbound

This paper cites Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:28.584837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47dd95ec-383b-410c-8c51-35816194e574 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:28.758982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0bb8e14-8396-4d4c-8910-d9e6f504d7bd · outbound

This paper cites Making Retrieval-Augmented Language Models Robust to Irrelevant Context.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Making Retrieval-Augmented Language Models Robust to Irrelevant Context

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:28.856770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8015dc7-d211-4107-bd14-faeb0176ae36 · outbound

This paper cites Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:28.967843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd6e5f72-302c-4cb8-b73c-55a44b05704a · outbound

This paper cites The power of noise: Redefining retrieval for rag systems.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking The power of noise: Redefining retrieval for rag systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.030937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a75db2-393a-4d82-b8ca-4a498a95cd2a · outbound

This paper cites Survey of hallucination in natural language generation.ACM computing surveys, 55(12):1–38, 2023.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Survey of hallucination in natural language generation.ACM computing surveys, 55(12):1–38, 2023

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.085138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343bd4b0-88e8-4505-9b6a-44802ec111db · outbound

This paper cites Statistical knowledge assessment for large language models.Advances in Neural Information Processing Systems, 36:29812–29830, 2023.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Statistical knowledge assessment for large language models.Advances in Neural Information Processing Systems, 36:29812–29830, 2023

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:32.486609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 30222594-8da4-4c99-bff5-a8c74e2ba688 · outbound

This paper cites Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-04T23:34:32.358622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ab6c7557-e124-45ae-89d8-d201a79d78a4 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.311633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1a5080-7a38-4bbd-9a85-e675f5f32108 · outbound

This paper cites Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.399438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6cbc35d-37ce-4d6e-bf21-19c59cf00418 · outbound

This paper cites Knowledge Boundary of Large Language Models: A Survey.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Knowledge Boundary of Large Language Models: A Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.460317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6da622af-7523-4f07-8e2a-45a5b68e80f1 · outbound

This paper cites Enhancing llm reliability via explicit knowledge boundary modeling.arXiv preprint arXiv:2503.02233, 2025.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Enhancing llm reliability via explicit knowledge boundary modeling.arXiv preprint arXiv:2503.02233, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.544029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0425caf5-6f61-44ad-8bf1-1a0c7d4111fe · outbound

This paper cites Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.602050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc78e5a1-3c5d-4d0c-be8b-c55dbb02d6ca · outbound

This paper cites Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-04T23:34:32.231695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a1205565-0489-46ed-b40d-1676704c3f05 · outbound

This paper cites Do Large Language Models Know What They Don't Know?.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Do Large Language Models Know What They Don't Know?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.746170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f921bb9-e4a2-49d9-9005-30064ede32e4 · outbound

This paper cites When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.815099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f16345-b060-4796-8efb-824d2deecb51 · outbound

This paper cites Are large language models more honest in their probabilistic or verbalized confidence? InChina Conference on Information Retrieval, pages 124–135.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Are large language models more honest in their probabilistic or verbalized confidence? InChina Conference on Information Retrieval, pages 124–135

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:32.469792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6f8e6300-6df4-4f39-b7d0-38136a0760b7 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:29.981733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 665aba2b-438d-435f-a8da-e66539ee39eb · outbound

This paper cites Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.024509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab214e8-25f8-45eb-b4c0-24b6f5708cda · outbound

This paper cites Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.107380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39e68d29-6ec3-4ee0-a0d3-c0e4146baa81 · outbound

This paper cites INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.174116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de94a82f-3c89-4211-b622-d7e63762e435 · outbound

This paper cites Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.240056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2117a3be-965e-4fb9-88c1-9b7d65165e53 · outbound

This paper cites LLM-Independent Adaptive RAG: Let the Question Speak for Itself.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking LLM-Independent Adaptive RAG: Let the Question Speak for Itself

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-04T23:34:32.146702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d8a53475-6b61-4b4d-8720-02d467d37a85 · outbound

This paper cites SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.390208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 293e6a61-5398-4d0a-9c92-18bfac964987 · outbound

This paper cites REPLUG: Retrieval-Augmented Black-Box Language Models.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking REPLUG: Retrieval-Augmented Black-Box Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.453151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab31e9af-defc-4f75-9cca-27569e613669 · outbound

This paper cites Query optimization for parametric knowledge refinement in retrieval-augmented large language models.arXiv preprint arXiv:2411.07820, 2024.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Query optimization for parametric knowledge refinement in retrieval-augmented large language models.arXiv preprint arXiv:2411.07820, 2024

Reference 31

Resolution: verified exact; raw_fallback, observed 2026-08-04T23:34:31.999347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cf66393b-573a-4e89-9832-145ac7a67c5c · outbound

This paper cites Understand what llm needs: Dual preference alignment for retrieval-augmented generation.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Understand what llm needs: Dual preference alignment for retrieval-augmented generation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:32.458311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f613b426-87c5-45f1-b7a1-3a487566885c · outbound

This paper cites Bridging relevance and reasoning: Rationale distillation in retrieval-augmented generation.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Bridging relevance and reasoning: Rationale distillation in retrieval-augmented generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.724409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c91241a-debf-4e80-a783-da2bdf65a134 · outbound

This paper cites Layer by Layer: Uncovering Hidden Representations in Language Models.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Layer by Layer: Uncovering Hidden Representations in Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.729282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d6fa640-ea61-411e-a4f8-da6b9361be6a · outbound

This paper cites Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:30.832661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b706d84-6d66-4a75-8fe9-9b5e1a8edfc3 · outbound

This paper cites The Internal State of an LLM Knows When It's Lying.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking The Internal State of an LLM Knows When It's Lying

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:31.046018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c79cef9d-08ef-41ed-b530-7dcac6de0f1f · outbound

This paper cites Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:31.202316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bda1feb-753b-42e4-b053-5c22f63397bf · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:31.304819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24061e83-22be-4108-b858-12f532ac33a3 · outbound

This paper cites The llama 3 herd of models.arXiv e-prints, pages arXiv–2407, 2024.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking The llama 3 herd of models.arXiv e-prints, pages arXiv–2407, 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:31.364185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c522172a-1dd5-409d-8dad-ce646b2e6142 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking Qwen2.5: A party of foundation models, September 2024

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:34:32.433403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.