Pith. sign in

Paper Citation Record · LEDGER

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality

As of 8 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 2 inbound Pith citation observations for arXiv:2507.08371.

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

pith.paper-citation-record.v1
2507.08371 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:26:32.580039Z

measured 55 of 55 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T14:29:23.383357Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T06:29:37.114956Z

Reference resolution

53 of 53 outbound references displayed

  • verified exact3
  • verified fuzzy14
  • unresolved35
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5fa9171d-7cdc-44a2-b052-4de017cf8eed · outbound

This paper cites FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.539981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.539981Z digest=sha256:5a67f08cc478e805da2e7096e68f9bedb2677a752236755930cc1c7f440c4ba3

Observation 10bd7166-7afd-4e16-8851-e2bffaeea726 · outbound

This paper cites The internal state of an llm knows when it’s lying.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality The internal state of an llm knows when it’s lying

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.561654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.561654Z digest=sha256:e76aeb8fb06917454168aba471285179dd0b4ba20aa191cd36d378281aa54415

Observation c2d1f2f1-3d9b-46d3-a6ac-9fe4a2cd7dd7 · outbound

This paper cites Quantifying memorization across neural language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Quantifying memorization across neural language models

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.639792Z

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=2026-08-06T18:26:29.585088Z digest=sha256:46d27416c44e4ff673d60055db5365af1301505a085eeece0cad22d67045925e

Observation c7cec484-9b1c-4aac-a67c-301ea314f96e · outbound

This paper cites an unresolved cited work.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.602304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.602304Z digest=sha256:982669aaebfc6539b153365a05b6920493506189a431c4cc9ca09969769cb3ec

Observation 9a34355f-9209-4472-8f72-5d04bb40d86f · outbound

This paper cites Decontextualization: Making sentences stand-alone.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Decontextualization: Making sentences stand-alone

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.621774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.621774Z digest=sha256:2f6e6129fd5af8e18ecaad9fa3e930a51f463dd2462c1de077a1a7cdc4f56a1c

Observation f1b5b387-49c1-481a-8639-36a54f0a106d · outbound

This paper cites The Llama 3 Herd of Models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality The Llama 3 Herd of Models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.639600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.639600Z digest=sha256:2156b8a35511efa4ad9382e52bea365ac266d1b92fca8da4676be2d597c0724a

Observation 3ac0fe54-5b97-49c6-92fa-57334fa1d7de · outbound

This paper cites Wiki medical terms, 2023.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Wiki medical terms, 2023

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.622878Z

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=2026-08-06T18:26:29.659186Z digest=sha256:4a33e48d1e6834c526ebaf929b778280f53c625d8a4ea7c5dd1a8ff7e676fc17

Observation 91dc7c5a-8778-4428-82e5-aba3d81ad997 · outbound

This paper cites an unresolved cited work.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.675631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.675631Z digest=sha256:740020dbb709d315f38d17ec02a0abf74b004a108ee17d150fd534ab5406d98a

Observation fdce8004-adf0-4b3a-ade3-f3594e75ef93 · outbound

This paper cites Understanding finetuning for factual knowledge extraction.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Understanding finetuning for factual knowledge extraction

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.607165Z

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=2026-08-06T18:26:29.705341Z digest=sha256:b9fa9d2d4be77fa135afef796428c6dc0e10923472b2ba23acfbb99e5b06046e

Observation 6f59c347-1575-4900-a37e-ded91ab93c51 · outbound

This paper cites Language models hallucinate, but may excel at fact verification.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Language models hallucinate, but may excel at fact verification

Reference 10

Resolution
verified exact
doi, observed 2026-08-06T18:26:32.850321Z

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=2026-08-06T18:26:29.791311Z digest=sha256:dab2c7e10dce4c493788e66c31328012a0d6f2d079bb6bf3c508bc0296810f9d

Observation a4a1fadc-3468-4d92-a262-12aa43a27b84 · outbound

This paper cites Molecular facts: Desiderata for decontextualization in LLM fact verification.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Molecular facts: Desiderata for decontextualization in LLM fact verification

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:29.860640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:29.860640Z digest=sha256:fb3d98229cefae768f2e7b1f3dfde5c4ea628a6f86d9a423a59bbcf42ea572f9

Observation f08e1922-808c-460a-ba79-da6f550fa10e · outbound

This paper cites Training language models on the knowledge graph: Insights on hallucinations and their detectability.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Training language models on the knowledge graph: Insights on hallucinations and their detectability

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.591457Z

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=2026-08-06T18:26:29.917261Z digest=sha256:e631fd8d82545f97206da1b3eb8038f4a2251fe619be43a5ea0bc97aedcc6943

Observation 3a454951-d313-4a5f-a688-f91ee821cf31 · outbound

This paper cites Lo RA : Low-rank adaptation of large language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Lo RA : Low-rank adaptation of large language models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.040221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.040221Z digest=sha256:9eaea91819601daf7c6db686449c68540845ff699e7ca18bec7f01fa31823969

Observation 4fae8eda-413c-4243-a5da-f6ec80780eb2 · outbound

This paper cites Training language models to generate text with citations via fine-grained rewards.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Training language models to generate text with citations via fine-grained rewards

Reference 14

Resolution
verified exact
doi, observed 2026-08-06T18:26:32.814398Z

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=2026-08-06T18:26:30.127824Z digest=sha256:14c15f0cc3f85a4f0a2a3e145df31630969207116c50576877529664eb1ad18d

Observation f19d4280-bb7d-47e6-9484-68ada67302dd · outbound

This paper cites Calibrating long-form generations from large language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Calibrating long-form generations from large language models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.202491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.202491Z digest=sha256:3137830e32b2d94d196830cc07e701ef90d2b1acc121fe1cef3c3ca98af5ba84

Observation 5e3ccf1f-6def-44b5-8d52-fd68e93e0ae6 · outbound

This paper cites Mistral 7B.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Mistral 7B

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.283507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.283507Z digest=sha256:64fc8bf6d9655623a6ec1cd3a88b904cfd3c888e8652b707e28061b24f6e2f73

Observation fab9d30b-b982-44b4-a3c6-14613442afb7 · outbound

This paper cites Teaching language models to hallucinate less with synthetic tasks.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Teaching language models to hallucinate less with synthetic tasks

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.552058Z

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=2026-08-06T18:26:30.374791Z digest=sha256:da60684d2ae84166cdd860fcbde1c5059011b026bcf900ea3fe4a719779fb2eb

Observation 37a4f50b-6f02-49b7-9377-e7921c4e8736 · outbound

This paper cites T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.457499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.457499Z digest=sha256:7b94019c081e77cf91d1036bd61955cb5cb71478ea5288001fb114b4fce34793

Observation abf81dc2-b600-4f22-b9b6-a0b99daff137 · outbound

This paper cites Personas as a way to model truthfulness in language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Personas as a way to model truthfulness in language models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.538465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.538465Z digest=sha256:9162ea0e6cbab5e3dbac62623cf1228ac6dadb46f2b46d192ddea78a0cf346e5

Observation d224623b-7aa7-4898-9796-e103d90bb414 · outbound

This paper cites Language Models (Mostly) Know What They Know.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Language Models (Mostly) Know What They Know

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.587552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.587552Z digest=sha256:6d5247441fff73060a610bf6b155f45dcb8eac43913571c6f6cb30f9ada4f7c4

Observation b49ce3dc-25d4-44a2-a2a8-c68a8e2e47af · outbound

This paper cites Unfamiliar finetuning examples control how language models hallucinate.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Unfamiliar finetuning examples control how language models hallucinate

Reference 21

Resolution
verified exact
doi, observed 2026-08-06T18:26:33.532384Z

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=2026-08-06T18:26:30.636277Z digest=sha256:e857512b91a9a3ac19a682ecef35117c2c9df4dda8ca35982d7fd1eb2cd7ab17

Observation e29002b0-0aaa-4a8a-b0f0-ca858660542c · outbound

This paper cites Gonzalez, Haotong Zhang, and Ion Stoica.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Gonzalez, Haotong Zhang, and Ion Stoica

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.691533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.691533Z digest=sha256:6b7ebd3bcfeced782ace88ed579d119ab2ca49e4d6c44fc17e6b594f41c4e668

Observation a88082c5-a14b-4bc6-9c42-d8e01d89c41e · outbound

This paper cites Factuality enhanced language models for open-ended text generation.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Factuality enhanced language models for open-ended text generation

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.490120Z

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=2026-08-06T18:26:30.754753Z digest=sha256:de9352d4c3107b99153be8d754dff05e201b0e6228252278eed4c2bcf4aacb5a

Observation cfb683b1-e6fa-4a2e-871d-d27197817731 · outbound

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

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Inference-time intervention: Eliciting truthful answers from a language model

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.470427Z

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=2026-08-06T18:26:30.811144Z digest=sha256:d730de6856b6b51202cf8be1e26baf487ce8b097aa8bdeec848508734e682156

Observation 31b5ba35-28f3-4107-a6e4-9036791b2d7f · outbound

This paper cites Flame : Factuality-aware alignment for large language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Flame : Factuality-aware alignment for large language models

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.451858Z

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=2026-08-06T18:26:30.860178Z digest=sha256:119ae7180f27c8be068c80dab198275eaf6bfa85e8b1c09b74d37e3e6e6133aa

Observation 75feda0d-e749-4f90-b94f-a65fb2139f43 · outbound

This paper cites Infini-gram: Scaling unbounded n-gram language models to a trillion tokens.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Infini-gram: Scaling unbounded n-gram language models to a trillion tokens

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.435710Z

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=2026-08-06T18:26:30.917285Z digest=sha256:df90d891dea13da61360776857c3de692e81fc42d9b04712ee2a6e03e839fb5f

Observation 828e64c0-8952-4226-8842-0dd9d243ebcf · outbound

This paper cites an unresolved cited work.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:30.980587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:30.980587Z digest=sha256:975021168c79735843b6692991bb811f3f875d36cc5c9c290b97a9a366960048

Observation 1ea0dcfd-de9d-4d23-a971-d28d46c509cd · outbound

This paper cites When not to trust language models: Investigating effectiveness of parametric and non-parametric memories.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality When not to trust language models: Investigating effectiveness of parametric and non-parametric memories

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.033851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.033851Z digest=sha256:ee75213097bc00abfa149b4f89444b1cc8b85ef9f6e007ce116aff136a5dd3be

Observation f8d3ee96-230a-4c81-a855-735ca8301990 · outbound

This paper cites Locally typical sampling.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Locally typical sampling

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.091058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.091058Z digest=sha256:3d13448882e1fe363e4d28a922c3d8b9d15034ed6e050997a023faf485daca7f

Observation 671d982e-2a3e-4fb3-8799-41966de17815 · outbound

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

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Gemma: Open Models Based on Gemini Research and Technology

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.144999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.144999Z digest=sha256:086a50832876bafff26a42929ac9a60507de0001e1bfc30918648bda3dc044ed

Observation aad77a80-435a-4abf-813d-d61e08975665 · outbound

This paper cites FA ct S core: Fine-grained atomic evaluation of factual precision in long form text generation.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality FA ct S core: Fine-grained atomic evaluation of factual precision in long form text generation

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.195944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.195944Z digest=sha256:e0f6546a95fc5e0d7680d369a608ef1b0a95d9e78ac6ebe79674ab7bccdfa0a6

Observation 48579606-20c6-4d84-9f4a-06e7414b7f6a · outbound

This paper cites Fine-grained hallucination detection and editing for language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Fine-grained hallucination detection and editing for language models

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.418850Z

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=2026-08-06T18:26:31.248302Z digest=sha256:6b30e4f18510b0881eda5cd8fbc572006bbd1c60c7d7d891642863ea530827f1

Observation c2f92d45-157c-4f97-8e79-36b12780c05e · outbound

This paper cites LLM s know more than they show: On the intrinsic representation of LLM hallucinations.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality LLM s know more than they show: On the intrinsic representation of LLM hallucinations

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.297228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.297228Z digest=sha256:77dd0b9834f0d8badf0b7f96e07ea5e86bcaf4fc1f83b9ce183b2fe086e6d472

Observation 646ac64f-cfb7-4244-aec1-3a1a32046420 · outbound

This paper cites Wikiplots, 2017.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Wikiplots, 2017

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.390817Z

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=2026-08-06T18:26:31.357540Z digest=sha256:d1330f6dbff2cc62bc859c1f2c8db54677096a4e483d4ce4dd9c3007a392ed8e

Observation f6c05270-b9a1-4cae-8064-3e54ac084821 · outbound

This paper cites Diversity.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Diversity

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.374739Z

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=2026-08-06T18:26:31.414151Z digest=sha256:8c0ef93cb75e6548c36ea320098c6c505aaaa03ff6fb2bf502e617f68b85601c

Observation 55c5061b-6b9a-4dbb-b918-2f6cec96348f · outbound

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

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Trusting your evidence: Hallucinate less with context-aware decoding

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.464160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.464160Z digest=sha256:b1b15c7d16f0746c74f0064b4ed8328aecb2e9e5aca74f23f0a829229f7edb76

Observation 971e9a7a-01bf-4519-a31d-5aff58fc18bf · outbound

This paper cites The curious case of hallucinatory (un)answerability: Finding truths in the hidden states of over-confident large language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality The curious case of hallucinatory (un)answerability: Finding truths in the hidden states of over-confident large language models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.511630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.511630Z digest=sha256:a04eccf306ab0243d11feb554d232a36cd71e67d35ac3349183eb41c36d7be6c

Observation acbe07aa-1e7f-47af-abfa-c8390a8dcc17 · outbound

This paper cites V eri S core: Evaluating the factuality of verifiable claims in long-form text generation.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality V eri S core: Evaluating the factuality of verifiable claims in long-form text generation

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.557522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.557522Z digest=sha256:eb8802b560466767ddc0981f92456b02ba8760401dcd127d23c403816b5ff86a

Observation c4fec76c-625a-426d-916c-7e3e715569c1 · outbound

This paper cites M ini C heck: Efficient fact-checking of LLM s on grounding documents.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality M ini C heck: Efficient fact-checking of LLM s on grounding documents

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.607675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.607675Z digest=sha256:87b58b0b1fbfc241a438694890889987e5c8d92127501c5b41ade3bd83159c08

Observation e9abe2ff-19da-45cc-a315-f720b09e72f2 · outbound

This paper cites Fine-tuning language models for factuality.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Fine-tuning language models for factuality

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.357444Z

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=2026-08-06T18:26:31.656453Z digest=sha256:aad1f02862bb2a846ad33dc81de4ad6442aabf32ca36143c0d6d423e570e0135

Observation 00b25911-59d2-460e-b502-c1ff4ea8fdd7 · outbound

This paper cites Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.711896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.711896Z digest=sha256:0f9ce1b6df08dd4d1d868cbdca3e6ec481a27dc038390603027c84394c67dfc5

Observation db1ac53c-1a78-4aba-9fb4-992366c40ae9 · outbound

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

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.773543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.773543Z digest=sha256:d6712ba83914b262aba0e441c01d2de062aa26665a7698137d1957e1df061677

Observation 7c8b3cf1-83f8-46c8-936f-37a1df93c09f · outbound

This paper cites A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.820584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.820584Z digest=sha256:f374e951b8ea27732b9a1533edf2f15f6b2726c6ac24ce92a92a769829f1eed7

Observation 233b1db7-9f1b-405d-af34-71792e5ef67c · outbound

This paper cites Factuality of large language models: A survey.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Factuality of large language models: A survey

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.877067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.877067Z digest=sha256:99c069104d85db057c3c4f75e7ffdbeb3d03b37e31e237d7e9b4be141240dfe1

Observation ad221bf8-33f8-414e-af84-ff009e78ed93 · outbound

This paper cites Redpajama: an open dataset for training large language models.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Redpajama: an open dataset for training large language models

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:26:33.331181Z

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=2026-08-06T18:26:31.926321Z digest=sha256:4cf6580874916246addfb72c93c8c41fc0e432023ca75481787bdba5f66a6ad8

Observation 7b13f32d-b1b6-448e-86c9-0927a2631646 · outbound

This paper cites Can LLM s express their uncertainty? an empirical evaluation of confidence elicitation in LLM s.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Can LLM s express their uncertainty? an empirical evaluation of confidence elicitation in LLM s

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:31.993597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:31.993597Z digest=sha256:aa5baaa386ff29151fec27a7bba2bf61efef94cab8e7701af352d4ace43d067c

Observation ddaf2dfa-df32-4d09-9212-19573b216ddd · outbound

This paper cites Alignment for Honesty.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Alignment for Honesty

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:32.071130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:32.071130Z digest=sha256:d24476897dcc30b713627787b16ccc042937b3b06e8461746db8fae96a1e11e0

Observation e3c8f5d7-1649-4d1d-b30e-afb0e8e4efc4 · outbound

This paper cites R -tuning: Instructing large language models to say ` I don ' t know '.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality R -tuning: Instructing large language models to say ` I don ' t know '

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:32.158740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:32.158740Z digest=sha256:a2142d6944206d079787fa6abac1e460168e4870e76e70e30a61f18a8b4bcb67

Observation c1196929-5aa3-4527-b52c-f392444418c8 · outbound

This paper cites an unresolved cited work.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-06T18:26:33.285157Z

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=2026-08-06T18:26:32.237919Z digest=sha256:243273d33d377d6865bdf8601b6b1b967815a7ab26d577d028e568b1c92cb8db

Observation 03d737ff-f7c8-4183-80ce-9e794ed12b11 · outbound

This paper cites write newline.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality write newline

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:32.310481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:32.310481Z digest=sha256:75b7bf3e501f5a8c1ad9a0f5725d88d846041543567ffe7b81bb138dec20723c

Observation b1a801e6-9109-4cdc-a3a0-f967dd7e67b8 · outbound

This paper cites @esa (Ref.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality @esa (Ref

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:32.393284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:32.393284Z digest=sha256:a5e67e90ef038f95d945b6bb4a7f03221dfb4157f496c7a93aca41be1367e676

Observation 635334c5-2f6a-48f1-af69-a837c06b0d62 · outbound

This paper cites an unresolved cited work.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Unresolved cited work

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T18:26:32.482874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:26:32.482874Z digest=sha256:e2623252d229cd9dcd4ad02e867cde0c32f860e8c27be8af95787a32a4df1781

Observation ad8c0ef7-e9b5-454a-83ff-27e94058c48b · outbound

This paper cites Lehrbuch der Geologie.

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality Lehrbuch der Geologie

Reference 53

Resolution
malformed identifier
raw_fallback, observed 2026-08-06T18:26:33.031595Z

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=2026-08-06T18:26:32.580039Z digest=sha256:68683365e997f2220e7e62de077425938b3338dedcacd9904d3d4dff99dac36d

Pith citing papers

Observation 7cc6a0fe-1ef3-4754-a3f5-89f0e09a0132 · inbound

Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness cites this paper.

Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-10T14:10:29.084655Z

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=2026-05-10T13:50:25.128014Z digest=sha256:b7436ad9ab7f0bc9cf1267042c1866d57654f16ff6357c46d73386b7eca31ff4

Observation e09ea66c-251b-46f1-b3c2-aeb5f0cf5fd5 · inbound

Finetuning with Scientific Data Increases Hallucinations: A Multi-domain Factuality Evaluation of LLMs cites this paper.

Finetuning with Scientific Data Increases Hallucinations: A Multi-domain Factuality Evaluation of LLMs The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-07-04T06:29:37.117175Z

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=2026-06-26T14:29:23.383357Z digest=sha256:fb36dfe0bb8ef24838468abaa6aef73e931638253596217f1b02709f4ea82adc