Pith. sign in

Paper Citation Record · LEDGER

TruthFlow: Truthful LLM Generation via Representation Flow Correction

As of 8 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 4 inbound Pith citation observations for arXiv:2502.04556.

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

pith.paper-citation-record.v1
2502.04556 v1

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T22:23:28.738176Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:33:48.011356Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

59 of 59 outbound references displayed

  • verified exact1
  • verified fuzzy8
  • unresolved50
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a2864384-b0f7-47c7-bbdf-2082d5fbefd4 · outbound

This paper cites GPT-4 Technical Report.

TruthFlow: Truthful LLM Generation via Representation Flow Correction GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.192931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.192931Z digest=sha256:5543df5f251897529cc9cab2c00e88988c55d5c1721622ab5adf9ad36be5e265

Observation 3818e60a-cff0-4246-b839-04b28c61f2ec · outbound

This paper cites Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.254012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.254012Z digest=sha256:e3d79f4b08ad1d4667338e17d773c913938bc90ccefe7e164410c7d855d28b93

Observation e24c2f5f-b285-484e-8858-4cf600f8fc70 · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction The Internal State of an LLM Knows When It's Lying

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.320617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.320617Z digest=sha256:db8e13d148fc2c9f349f1947d3c308542419192339f40d254f94e597d3a36a98

Observation 3cdc8482-1021-4ae2-b7b5-63c2a1112dcf · outbound

This paper cites Qwen Technical Report.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Qwen Technical Report

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.350971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.350971Z digest=sha256:cff683145a821720c05aaa9e9f58bb59f6eba39cffb557636b4c27af25b54d3e

Observation 9c917423-b91d-4138-a46e-bc305100f03b · outbound

This paper cites F., Liu, X., Jagadish, H., and Wang, L.

TruthFlow: Truthful LLM Generation via Representation Flow Correction F., Liu, X., Jagadish, H., and Wang, L

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.561691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:27.354733Z digest=sha256:4e741238ec060a43dade905ce05067f06685c0061123066de66259629bbbae03

Observation 3b003863-bb5e-474e-8730-6778ee43d89f · outbound

This paper cites an unresolved cited work.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-08T22:23:29.487980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:27.358845Z digest=sha256:8c5c81f53ca0f679ecd1e52899ff1ea42c8a79d4baf4f21da2c080d25709ac69

Observation 9dbca40c-cdbd-44d1-8860-f76e512d073c · outbound

This paper cites Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.362479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.362479Z digest=sha256:a1b15441ac366915115ddb9a6a382d9a9d700b552276ce6e90c720f76489ceb0

Observation 0562b58a-3f5d-476b-87f7-72d7fd21ae64 · outbound

This paper cites Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.430340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.430340Z digest=sha256:b2dddb962effc4eec42b1652fe1300e77a071d477a4f001b31aad1b0285f378e

Observation 8f12cd1d-928d-4dad-8eb7-ce13dc188a92 · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.507483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.507483Z digest=sha256:afff212f454ffc6d2feb4825e9522a516d2a154eae039d11e4f6842df532d7a4

Observation 48e60b3d-9bdc-49ea-a7a6-ab95de8f0d4b · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.534094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.534094Z digest=sha256:8abf002a7de3df8fa61f8c2936f2501606789a063398c82660b4bb03de4a92c7

Observation fc1fb706-b76e-4937-9fcc-fd9c4400c00a · outbound

This paper cites Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-08T22:23:29.149431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:27.538328Z digest=sha256:958355333afd63eedeef3a0438082ff67acda1d68a902c5dbfedc601ee439321

Observation df555452-e19f-42d0-b783-2653d6ac2cba · outbound

This paper cites In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation.

TruthFlow: Truthful LLM Generation via Representation Flow Correction In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.541432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.541432Z digest=sha256:c0d9174348d3743de63f298a51dafdac27e472ff1925d73dcb23929714ed9ab4

Observation 0f2236e7-28e7-4254-bec9-28aa3f8d733f · outbound

This paper cites GRATH: Gradual Self-Truthifying for Large Language Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction GRATH: Gradual Self-Truthifying for Large Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.545341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.545341Z digest=sha256:68a047b2681adcadca76fac100048a6e561989c14c040ca7b9341192840cce61

Observation 201869d0-430e-4dd7-9084-999be4ef0c05 · outbound

This paper cites Truth forest: Toward multi-scale truthfulness in large language models through intervention without tuning.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Truth forest: Toward multi-scale truthfulness in large language models through intervention without tuning

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.477652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:27.595829Z digest=sha256:e31bba6514566450e79402e45371a53a786b56cfe6bd69d6ef4f2abdf7afe87e

Observation 3e289c78-b1fe-4411-ae9c-dc45a90603ba · outbound

This paper cites DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.687156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.687156Z digest=sha256:01d3f7c65f7134181ce77b00f0a9f1b896a2c7835ce2e78352896934eb2eece9

Observation f68cfb77-be29-4af9-b752-46c146693ebb · outbound

This paper cites HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection.

TruthFlow: Truthful LLM Generation via Representation Flow Correction HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.744278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.744278Z digest=sha256:cfc45613cbf0be774dcf7539a5e9e4280a66009dac57287c51bdfbfa95fed5dd

Observation 787cb7f5-6728-4149-9707-f5c3d3763c73 · outbound

This paper cites The Llama 3 Herd of Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction The Llama 3 Herd of Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.754085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.754085Z digest=sha256:6621c8756cfd59390f302057bce2fb757437f86e335c40bc7bde0a3e82910ea8

Observation 6c11c963-594f-4313-bb89-20419926711c · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Scaling rectified flow transformers for high-resolution image synthesis

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.758535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.758535Z digest=sha256:0cb01e52d74b736458bae38cf472b1c154085d4a43601d9470d0a40b5c2d053f

Observation 83ad5505-3f12-4c00-bfce-1b79a568c449 · outbound

This paper cites Institutionum calculi integralis, volume 4.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Institutionum calculi integralis, volume 4

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.460372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:27.762113Z digest=sha256:72da993636654f87e1431d27d0fb341efec598385ba8fe878f1395ae0c187af8

Observation 09f6ea34-236b-41c8-acbc-548facdc5fc8 · outbound

This paper cites Non-Linear Inference Time Intervention: Improving LLM Truthfulness.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Non-Linear Inference Time Intervention: Improving LLM Truthfulness

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.765808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.765808Z digest=sha256:f19bd77fde2bb097a851bd83f5279ca163668fea4fe83c9e414a5452a1c65a13

Observation a3af8d04-62d3-4be0-b553-0a72efb441f8 · outbound

This paper cites Mitigating Large Language Model Hallucination with Faithful Finetuning.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Mitigating Large Language Model Hallucination with Faithful Finetuning

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.819703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.819703Z digest=sha256:31f36712b4cbbbeeb95f4f5abee72db787339d0009f4738a5c35e974977b5400

Observation 68c342f0-6d71-40c0-bfc1-b1ef84d71f66 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

TruthFlow: Truthful LLM Generation via Representation Flow Correction A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.915938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.915938Z digest=sha256:acc5269d883fcea06088b6affe71e5df4ede2c2b44f021b859275f52db9040dc

Observation a7f212f7-7f0f-4b11-a696-c8e4635fd91f · outbound

This paper cites J., Madotto, A., and Fung, P.

TruthFlow: Truthful LLM Generation via Representation Flow Correction J., Madotto, A., and Fung, P

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.954263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.954263Z digest=sha256:2e5b46fa7a23e4fc27e2948841d7be86e38e5f278aa6b69f40b4341acf4f8427

Observation c86aba22-2696-4246-9a7f-c28467b2237c · outbound

This paper cites Mistral 7B.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Mistral 7B

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.962031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.962031Z digest=sha256:8abe6ac4e516787f318f83ddd5d1218f09a83f3fd9c549bd01e98a9e81569a24

Observation d4480f36-b2cd-493f-bf97-3b06d174a7db · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.966500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.966500Z digest=sha256:bcd75316c24f4c409134fb61ed80b14f1c0bc826065048fef041f59f374c6397

Observation b3e1e005-5edf-4283-ae6e-3b368ca8b285 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

TruthFlow: Truthful LLM Generation via Representation Flow Correction TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.970336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.970336Z digest=sha256:e0fc92989b5ad4b3b068f2de2bd3a036bd77524fc28982921e2b7bba7c82be60

Observation b4a7d798-0b2a-4103-adad-0731163b13f0 · outbound

This paper cites SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully.

TruthFlow: Truthful LLM Generation via Representation Flow Correction SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:27.974474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:27.974474Z digest=sha256:51ba61ad6be64edf0bb3c602bb18775d5601a35d55ed982e822ec5e1f3c51dde

Observation b918dc1f-940b-4089-a7b8-07212c30b8a9 · outbound

This paper cites Beitrag zur n \"a herungsweisen Integration totaler Differentialgleichungen.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Beitrag zur n \"a herungsweisen Integration totaler Differentialgleichungen

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.436488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:28.029424Z digest=sha256:15b2221a5eeeb14987d517d030a233c2c2fcafb46a59bbd9865c1c8225457d41

Observation 7b0c6773-0735-415f-8ee4-8b872093c1e2 · outbound

This paper cites Natural questions: a benchmark for question answering research.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Natural questions: a benchmark for question answering research

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.426143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:28.081014Z digest=sha256:8bc130eb0b827ddff84e300f2f2cd140297ca8f84cc65bd85d9370b625997155

Observation 6ca2f42b-d331-4589-86bd-2e4ab0f39882 · outbound

This paper cites u ttler, H., Lewis, M., Yih, W.-t., Rockt \.

TruthFlow: Truthful LLM Generation via Representation Flow Correction u ttler, H., Lewis, M., Yih, W.-t., Rockt \

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.171509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.171509Z digest=sha256:e077bb8fd034507e48ab69c7c7993d88d13780cca5b99169b8a96710479c22f6

Observation ba465a51-296c-4227-881a-eef3ca3c7eed · outbound

This paper cites HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.190876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.190876Z digest=sha256:cdf9da908569f8252aa326b617cc81e5d1d684bf6a8ab6ce7c051b9d7875c35a

Observation 07e814d5-44aa-43ba-a0b4-04dc2a809c0a · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Inference-time intervention: Eliciting truthful answers from a language model

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.199961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.199961Z digest=sha256:60ad3d27b30dc8b8111bcb20d8d7b5c150d8ecbe7924396ae80c55bd3f2eeefa

Observation 0b112ed8-4537-4c86-8cbb-ec1d4b7b0808 · outbound

This paper cites Contrastive Decoding: Open-ended Text Generation as Optimization.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Contrastive Decoding: Open-ended Text Generation as Optimization

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.203920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.203920Z digest=sha256:9ca41399cf0b27c20cb63021e50424a4f001e18c05afd15f1cd3141b008b354a

Observation c2a72bfb-fe41-4d23-b752-3ca5ea9bc3c7 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

TruthFlow: Truthful LLM Generation via Representation Flow Correction TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.209103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.209103Z digest=sha256:30b913380973772bb9800f0ab76e4a73e6d1ade7bba4a7a961e7d110ba3f4b62

Observation b0733e87-75d2-4eaf-b163-0ad3baeb2e1e · outbound

This paper cites Flow Matching for Generative Modeling.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Flow Matching for Generative Modeling

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.212853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.212853Z digest=sha256:bd091705dbf51ac074f17095a673da2c877ac363731c7444358ae5e113010076

Observation c04a9a4f-0fa6-42ba-ade7-812b9f983853 · outbound

This paper cites DeepSeek-V3 Technical Report.

TruthFlow: Truthful LLM Generation via Representation Flow Correction DeepSeek-V3 Technical Report

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.265727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.265727Z digest=sha256:1c6397cb5344233651e7d1b807c662b11cde141e3353815180d9f927845bd114

Observation 31112765-95d2-4c20-900e-0e8502bb4c9e · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.371568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.371568Z digest=sha256:044c5e1765343344fec6c91741aaa830c38f63213a0279d993d62c7cd9d6b5da

Observation ef38339d-0b30-41fa-b882-91079f074a33 · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.406670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.406670Z digest=sha256:ca8431d6d5c93aa4f843effea2e93d6a6875f36ff7d2b98e2bbb90dd22cd0665

Observation d86a6608-8fc0-4e76-a084-e37eab375ce2 · outbound

This paper cites Probing llms for logical reasoning.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Probing llms for logical reasoning

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.402763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:28.417749Z digest=sha256:be5289d8dfe47bf94799672aaa7707c3ac3d4f4909773e91c9dca84bbb2df50c

Observation 4f19e940-c736-4ddf-a7e1-fcbdc487e549 · outbound

This paper cites Contrastive Decoding Improves Reasoning in Large Language Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Contrastive Decoding Improves Reasoning in Large Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.424314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.424314Z digest=sha256:4ea4a641ea8607a0c0503c0a3fe235ba0a12a76721bf1eb8a5b2a940b9bf1a8f

Observation be610d12-d9aa-4ca7-adf8-ce4398e469e0 · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction Training language models to follow instructions with human feedback

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.428397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.428397Z digest=sha256:09736d0c38186ad1936226dd5482b332a5d860176b993c1450a4329e892e1b17

Observation 87436ef0-890a-4c96-becb-d13c5b1257e8 · outbound

This paper cites Med-HALT: Medical Domain Hallucination Test for Large Language Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Med-HALT: Medical Domain Hallucination Test for Large Language Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.432815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.432815Z digest=sha256:072ab1ba3235ee81e0f93b17750021724472499480971ed6d7c42563e4e51c87

Observation 91ac5a9d-a185-43c2-82d1-08e16e47ddbd · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Steering Llama 2 via Contrastive Activation Addition

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.437300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.437300Z digest=sha256:c46c7877b0a18572a94a6d064e35340f50d376e724934e8ad27bca3e12fdf2b7

Observation 597c427e-b712-4dba-8951-9fd641b294a8 · outbound

This paper cites D., Ermon, S., and Finn, C.

TruthFlow: Truthful LLM Generation via Representation Flow Correction D., Ermon, S., and Finn, C

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.441246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.441246Z digest=sha256:8f53d57a3d6010de64d35bd7dfc52d4da92ebae4ac3e76e71c728c92b63bea99

Observation 46460980-2a9e-4f90-a1b3-e2035a6369c7 · outbound

This paper cites A Survey of Hallucination in Large Foundation Models.

TruthFlow: Truthful LLM Generation via Representation Flow Correction A Survey of Hallucination in Large Foundation Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.444572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.444572Z digest=sha256:7f3de557e06833a9c42281785efccb8a622da4b4203bd42846101112948c3f32

Observation 456845d6-660b-4a3c-930a-b9e16efecb11 · outbound

This paper cites an unresolved cited work.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-08T22:23:29.375574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:28.447601Z digest=sha256:9e91605ce5ade3a2a3af2b91719c4b946941d3be137d105e7d2f7a5dcc85f257

Observation b5ad759b-1650-4294-b34c-c665fd51e3e2 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

TruthFlow: Truthful LLM Generation via Representation Flow Correction U-net: Convolutional networks for biomedical image segmentation

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.451311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.451311Z digest=sha256:460f8a8bae71e3046d167b320732818b51f538a06d564ea5d6a34b48fbd24d52

Observation 0be1d27a-1b33-46ad-a09b-37d1f57a3e82 · outbound

This paper cites U ber die numerische aufl \.

TruthFlow: Truthful LLM Generation via Representation Flow Correction U ber die numerische aufl \

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.357856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:28.454488Z digest=sha256:d46f33a0b5e2f7c202cc6860906350753d5080e87c9061260d3489226ae532f5

Observation daac12ba-004d-42f7-9d22-8bc25331a672 · outbound

This paper cites BLEURT: Learning Robust Metrics for Text Generation.

TruthFlow: Truthful LLM Generation via Representation Flow Correction BLEURT: Learning Robust Metrics for Text Generation

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.458217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.458217Z digest=sha256:5d3bd4334aa24fa2a85857aeaeff0ea4c3b3dff322a833b1bcd436b793b06dcc

Observation a62c728a-fea2-4da8-aee2-f0ee5cc5c77d · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Gemma: Open Models Based on Gemini Research and Technology

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.462488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.462488Z digest=sha256:0eb695b17a9e668676db00fc5e55be1c186a8fb2e2fb48e3dbb38b244bf3c0da

Observation 4fe22985-3b68-4fd6-939a-1d25156a0fd1 · outbound

This paper cites Fine-tuning Language Models for Factuality.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Fine-tuning Language Models for Factuality

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.466620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.466620Z digest=sha256:011e54a79df252043fb5373dc469b946a7641c5012eea7a1fcd6db7404c0cfeb

Observation 84c669bc-1a15-4dce-a263-8e05c6ab312a · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.470232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.470232Z digest=sha256:ac3d3fb80939f2f72ce88b53d8d39a661117f3d96d9805ddede96062eb0782fd

Observation f93ee7fb-d2fb-444f-b33c-a001ece16d12 · outbound

This paper cites Attention is all you need.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Attention is all you need

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.500981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.500981Z digest=sha256:81d0020f100096019496bd1f4cc151d667d4b25ad9e991314bfc1e6585060217

Observation dccf0263-ad27-449d-9892-7fc9035d1282 · outbound

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

TruthFlow: Truthful LLM Generation via Representation Flow Correction HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.556369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.556369Z digest=sha256:5aa35c6e8c7fc961f13ef2c92672153f71a5db26eff76f038320a798eeb6a6d5

Observation 190d6256-a71b-4efb-a652-648797113d44 · outbound

This paper cites TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space.

TruthFlow: Truthful LLM Generation via Representation Flow Correction TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.595116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.595116Z digest=sha256:60a4d66710d475591fd94f2add56334d24d2cdbb7291a90c53031d3e7f56dd57

Observation d18f4ee2-97aa-4236-892c-8cd7d6b99b47 · outbound

This paper cites Alleviating Hallucinations of Large Language Models through Induced Hallucinations.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Alleviating Hallucinations of Large Language Models through Induced Hallucinations

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.641619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.641619Z digest=sha256:bb5f0f89afee7a9349dde976825b918cc302c516662d543c0d1cfbfee1ac407b

Observation 4e2be219-7c2c-46d3-906e-f41177bee29e · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Representation Engineering: A Top-Down Approach to AI Transparency

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.678697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.678697Z digest=sha256:b9043943232641e9f1dfc0343500309b19f2365e9cedb95ce76735609b6088a1

Observation 7490333d-c274-4b8c-b62c-e5a8ccffff81 · outbound

This paper cites Z., Fredrikson, M., and Hendrycks, D.

TruthFlow: Truthful LLM Generation via Representation Flow Correction Z., Fredrikson, M., and Hendrycks, D

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T22:23:29.295766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-08-08T22:23:28.721264Z digest=sha256:0b722f65acba4a8faf2ad591a62bf35c9ba5beb8bc49d2861b9defe913fe9814

Observation 83baf9cc-db12-4b9f-97b5-a837c9ef14fb · outbound

This paper cites write newline.

TruthFlow: Truthful LLM Generation via Representation Flow Correction write newline

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-08T22:23:28.738176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T22:23:28.738176Z digest=sha256:265d99e8bc94f570b7f33cee9e8a23441a90358ce616a6853d3a5d6c20c229de

Pith citing papers

Observation cd4c73eb-1e49-4e00-918c-6c288c0a0a60 · inbound

Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning cites this paper.

Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning TruthFlow: Truthful LLM Generation via Representation Flow Correction

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T14:33:48.011356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T14:33:48.011356Z digest=sha256:a167904e9161cae4ae7d4802e489f0241d53077984df1bee26be5cf74a6c4adb

Observation 9a47c79d-66b7-49ac-9c4f-2ead060a57a0 · inbound

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing cites this paper.

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing TruthFlow: Truthful LLM Generation via Representation Flow Correction

Reference 49

Resolution
verified exact
arxiv_id, observed 2026-05-16T08:17:36.552368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-16T08:12:55.296932Z digest=sha256:ed38419f7c0d33f53ccc804e4a59ce7b17c8e7190a008103bc0b23b5828c28d9

Observation a1686da3-46da-49c8-8909-707253a82eef · inbound

Steer Like the LLM: Activation Steering that Mimics Prompting cites this paper.

Steer Like the LLM: Activation Steering that Mimics Prompting TruthFlow: Truthful LLM Generation via Representation Flow Correction

Reference 3

Resolution
metadata mismatch
arxiv_id, observed 2026-05-09T01:59:34.588602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=arxiv_source observed=2026-05-07T16:20:10.078995Z digest=sha256:f99b4d1649b5d5a3689df965851129205257e757f1aeba303818bfb9b18be829

Observation 3d32d3e8-4142-44f1-b257-9eae980a5405 · inbound

Can Factual Opinions Be Edited (Manipulated) in Large Language Models? cites this paper.

Can Factual Opinions Be Edited (Manipulated) in Large Language Models? TruthFlow: Truthful LLM Generation via Representation Flow Correction

Reference 2

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T02:56:29.000039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T10:30:47.603024Z digest=sha256:6a350d9f53ed7bf39a50d1b85ef8a764561fd333bafc6b673d5a28ae169fc720