Pith. sign in

Paper Citation Record · LEDGER

Exploring the generalization of LLM truth directions on conversational formats

As of 20 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2505.09807.

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

pith.paper-citation-record.v1
2505.09807 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:27:24.651589Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

20 of 20 outbound references displayed

  • verified exact0
  • verified fuzzy5
  • unresolved14
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 137d9230-f3d0-4b92-bcc2-2cc8e8b179aa · outbound

This paper cites Park, Simon Goldstein, Aidan O’Gara, Michael Chen, and Dan Hendrycks.

Exploring the generalization of LLM truth directions on conversational formats Park, Simon Goldstein, Aidan O’Gara, Michael Chen, and Dan Hendrycks

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.575933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.575933Z digest=sha256:ddb4b21ac289f2c263521a11628da7291607b71b7347496578a5055677507f6f

Observation 9a8b5476-6a4c-44ea-8c99-aff4f4725ddd · outbound

This paper cites Deception abilities emerged in large language models.

Exploring the generalization of LLM truth directions on conversational formats Deception abilities emerged in large language models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.580238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.580238Z digest=sha256:caa70ce1b916af6acd52f94c318a17dd3c607d0dfa452747036e38a11fc9ee05

Observation 19a59d3b-2c6c-4470-9a02-55ba4b1c3b5a · outbound

This paper cites Large language models can strategi- cally deceive their users when put under pressure.

Exploring the generalization of LLM truth directions on conversational formats Large language models can strategi- cally deceive their users when put under pressure

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T21:27:24.921448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.584327Z digest=sha256:ecf81ff782c80fa0ea8c7cf52858bbaae966d4db0d5f15b83c25c4e88078fd43

Observation c0262941-7900-47fc-9ae6-c74155c83ceb · outbound

This paper cites an unresolved cited work.

Exploring the generalization of LLM truth directions on conversational formats Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.588566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.588566Z digest=sha256:67f1b45eaceb1ee9873289bb699b82e29462fa03980e6088542230faad5274d3

Observation be4a7bf1-3b88-4aa2-a07b-e8ccdbcfdcc2 · outbound

This paper cites Discovering latent knowledge in language models without supervision.

Exploring the generalization of LLM truth directions on conversational formats Discovering latent knowledge in language models without supervision

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.592148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.592148Z digest=sha256:097466be77249916dbbe939f6da608ef0113449b29c96c27f461a92b6001490b

Observation 1ab742cc-15a0-44f9-8639-b3a20fd40818 · outbound

This paper cites The internal state of an LLM knows when it‘s lying.

Exploring the generalization of LLM truth directions on conversational formats The internal state of an LLM knows when it‘s lying

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.596433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.596433Z digest=sha256:fb3d3b9155b7e97438822cb02da2358dd0ca1c6b8a3b51b4a9c529ac01c74409

Observation 58c66133-ad7e-4dab-8163-8836eaccf422 · outbound

This paper cites an unresolved cited work.

Exploring the generalization of LLM truth directions on conversational formats Unresolved cited work

Reference 7

Resolution
malformed identifier
raw_fallback, observed 2026-08-15T21:27:24.898282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.600611Z digest=sha256:a2cc198b7c7c98cea0e3ff1532cb27d947ec84f241f021513604ae8468f0b760

Observation e114301b-89f2-4aa9-ba05-8c1b6e2440e3 · outbound

This paper cites LLM internal states reveal hallucination risk faced with a query.

Exploring the generalization of LLM truth directions on conversational formats LLM internal states reveal hallucination risk faced with a query

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.604246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.604246Z digest=sha256:68f0aecc3be218d165e3750e052160f931f038bda33225bd4f7ac4a6ff9318f5

Observation d2d905dc-59e8-47b5-89d0-83f99984ce85 · outbound

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

Exploring the generalization of LLM truth directions on conversational formats Representation Engineering: A Top-Down Approach to AI Transparency

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.607834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.607834Z digest=sha256:e163214036cbbde353b653c34542724d8fbf589d280ed4189951560cdf522313

Observation acd2bbb5-b2ce-416e-914f-643d50d9753a · outbound

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

Exploring the generalization of LLM truth directions on conversational formats Inference- time intervention: Eliciting truthful answers from a language model

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T21:27:24.886188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.611790Z digest=sha256:e56853d890d490ff8ae5ce9e774d7184d4a51963f014176d190ccee0ad33029f

Observation 4fad1656-eef6-43e7-9aff-79118f3247a8 · outbound

This paper cites An information-theoretic study of lying in LLMs.

Exploring the generalization of LLM truth directions on conversational formats An information-theoretic study of lying in LLMs

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T21:27:24.874878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.615154Z digest=sha256:8db3a25d538ddec61901e8f708fec05686aa6df29d98466e385f248b372b0fca

Observation 69bb101a-d480-4d0f-9ef8-c288ce7c85ec · outbound

This paper cites How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions.

Exploring the generalization of LLM truth directions on conversational formats How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.618661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.618661Z digest=sha256:ec7319cb6aebea70bc65c0a00cabe45c15bec7c56916a350d2a07ea33bc0dd4b

Observation 63fb69e4-5980-4d31-81fd-786888e1b5f4 · outbound

This paper cites an unresolved cited work.

Exploring the generalization of LLM truth directions on conversational formats Unresolved cited work

Reference 13

Resolution
unresolved
raw_fallback, observed 2026-08-15T21:27:24.862628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.623699Z digest=sha256:4849f1f4714df3444a8a7ff4ca3a8be7fd0514e698b69c5286e41ddd0211951f

Observation f6e51056-8ef1-40a8-bf97-3ab814b3556d · outbound

This paper cites The geometry of truth: Emergent linear structure in large lan- guage model representations of true/false datasets.

Exploring the generalization of LLM truth directions on conversational formats The geometry of truth: Emergent linear structure in large lan- guage model representations of true/false datasets

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.631548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.631548Z digest=sha256:ea759e0a40441dadbf531b2960d3ede5838484ded21689593bd1a790559b5e85

Observation a446b579-e5a3-416f-b92b-ae6a942fb251 · outbound

This paper cites Hamprecht, and Boaz Nadler.

Exploring the generalization of LLM truth directions on conversational formats Hamprecht, and Boaz Nadler

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T21:27:24.838175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.639602Z digest=sha256:131dd2f14b956185abb55f3207ee78fb16b695de8ba2871c27eff57a3b16d06c

Observation 18ba1c95-41e4-4a3b-b95b-57d2165c6690 · outbound

This paper cites Levinstein and Daniel A.

Exploring the generalization of LLM truth directions on conversational formats Levinstein and Daniel A

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.643131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.643131Z digest=sha256:2716373e96de24e63eecabb7d05fe3baa05af2680f2b54e2d2157c0d23db75a4

Observation c58fb9d8-6c3f-4b16-9ff7-17d96d76b405 · outbound

This paper cites Llama 3 model card.

Exploring the generalization of LLM truth directions on conversational formats Llama 3 model card

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.646997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.646997Z digest=sha256:e3b2daf8858629fbeffecf94397f9ae60f69bda73f12b68488a8efe52c56fcf5

Observation 6bd90363-fe88-4fd9-b0d2-400a00700b00 · outbound

This paper cites Ministral-2410-8b.

Exploring the generalization of LLM truth directions on conversational formats Ministral-2410-8b

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T21:27:24.819410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T21:27:24.651589Z digest=sha256:41904f33965d72e08b5498770b5a49d644d085d469ebabe4b00e65905f228381

Observation f6ec88a8-03b3-4710-a2ce-ff66dfff592b · outbound

This paper cites doi: 10.18653/v1/2023.emnlp-main.291.

Exploring the generalization of LLM truth directions on conversational formats doi: 10.18653/v1/2023.emnlp-main.291

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.627946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.627946Z digest=sha256:dce20b4a8ae5dfa9162a705bf0956dcb95d83d33fafa2da1c3e5f6492a9fe477

Observation 283e5bbc-6cf9-4e4f-b471-8e8bbcdd72d7 · outbound

This paper cites an unresolved cited work.

Exploring the generalization of LLM truth directions on conversational formats Unresolved cited work

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-15T21:27:24.635591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:27:24.635591Z digest=sha256:f3c915db5482d45e5a0c564877b21464805a501206cf43c6c2783c45d3c1c33c

Pith citing papers

No inbound Pith citation observations are available.