Paper Citation Record · LEDGER

Causal Evidence that Language Models use Confidence to Drive Behavior

As of 6 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2603.22161.

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

pith.paper-citation-record.v1
2603.22161 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T09:43:05.524088Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T07:44:53.539382Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-30T08:04:28.791842Z

Reference resolution

31 of 31 outbound references displayed

verified exact19
verified fuzzy7
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f7308fc9-0d04-40a0-95c2-172a147433e0 · outbound

This paper cites Emergent introspective awareness in large language models.https://transformer-circuits.

Causal Evidence that Language Models use Confidence to Drive Behavior Emergent introspective awareness in large language models.https://transformer-circuits

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:06.010719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 86e942f4-f9a0-4d2b-bff0-b8cac6159c32 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Causal Evidence that Language Models use Confidence to Drive Behavior On the Opportunities and Risks of Foundation Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.689507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3eae1ae1-2b90-47f0-8fef-0bec7d8477ec · outbound

This paper cites Learning to Route LLMs with Confidence Tokens.

Causal Evidence that Language Models use Confidence to Drive Behavior Learning to Route LLMs with Confidence Tokens

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.693586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6b8b511d-cb66-4a6b-9920-2d0dc35e0759 · outbound

This paper cites How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings.

Causal Evidence that Language Models use Confidence to Drive Behavior How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:05.995667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4ecf6f20-63b9-4d3a-90bb-e7819b50dd14 · outbound

This paper cites arXiv preprint arXiv:2510.20487 , year =.

Causal Evidence that Language Models use Confidence to Drive Behavior arXiv preprint arXiv:2510.20487 , year =

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.661418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a230a5ef-8473-48e2-9756-984cf68c438e · outbound

This paper cites an unresolved cited work.

Causal Evidence that Language Models use Confidence to Drive Behavior Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-21T09:44:06.014528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e98251f9-7940-4836-8963-eac4a6166453 · outbound

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

Causal Evidence that Language Models use Confidence to Drive Behavior Language Models (Mostly) Know What They Know

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.704774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6d145a09-a089-4a57-b2ac-73c88462ef51 · outbound

This paper cites Why Language Models Hallucinate.

Causal Evidence that Language Models use Confidence to Drive Behavior Why Language Models Hallucinate

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.686530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aff98b5a-48b7-42cc-b2d0-b06ea3806efc · outbound

This paper cites AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions.

Causal Evidence that Language Models use Confidence to Drive Behavior AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.708549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d1dde2f7-5e39-47fd-983a-ff8358f5b8e5 · outbound

This paper cites How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models.

Causal Evidence that Language Models use Confidence to Drive Behavior How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T09:44:05.642922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f091fd4c-f072-403c-a475-1c593a7ef720 · outbound

This paper cites Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models.

Causal Evidence that Language Models use Confidence to Drive Behavior Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.697748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aef1ead6-cfc4-4a16-803c-ad59249925c1 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Causal Evidence that Language Models use Confidence to Drive Behavior Steering Llama 2 via Contrastive Activation Addition

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.664653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 62e24b5d-6bee-4a4e-b606-6396c400275f · outbound

This paper cites Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A.

Causal Evidence that Language Models use Confidence to Drive Behavior Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.679600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aea92f4e-fd01-4c94-9002-79c85ff8efab · outbound

This paper cites Sentence-BERT: Sentence embeddings using Siamese BERT-networks.

Causal Evidence that Language Models use Confidence to Drive Behavior Sentence-BERT: Sentence embeddings using Siamese BERT-networks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:06.013588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c4363e52-b8a2-456a-8a84-b2de1811b75a · outbound

This paper cites Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting.

Causal Evidence that Language Models use Confidence to Drive Behavior Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.678228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5dfb1e7c-45b7-49f4-88b0-b96f06523101 · outbound

This paper cites Improving Instruction-Following in Language Models through Activation Steering.

Causal Evidence that Language Models use Confidence to Drive Behavior Improving Instruction-Following in Language Models through Activation Steering

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.683170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 82d38082-ecdf-401c-8854-f51fd3962bd9 · outbound

This paper cites Revisiting Uncertainty Estimation and Calibration of Large Language Models.

Causal Evidence that Language Models use Confidence to Drive Behavior Revisiting Uncertainty Estimation and Calibration of Large Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.672258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c860152e-3ff7-4350-a450-6abed1da25e8 · outbound

This paper cites Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback.

Causal Evidence that Language Models use Confidence to Drive Behavior Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T09:44:05.651338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 56a8d8cf-3450-4091-87fd-117dcfb5e0c5 · outbound

This paper cites Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy.

Causal Evidence that Language Models use Confidence to Drive Behavior Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.676218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f869d2c4-6ddf-4f0a-99f6-b503deed5e67 · outbound

This paper cites Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations.

Causal Evidence that Language Models use Confidence to Drive Behavior Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.657840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 38e1e6ec-1851-41aa-a05d-87d3749a595a · outbound

This paper cites Steering Language Models With Activation Engineering.

Causal Evidence that Language Models use Confidence to Drive Behavior Steering Language Models With Activation Engineering

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.675051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a2229f91-e9b7-4dba-96af-229625db583b · outbound

This paper cites Measuring short-form factuality in large language models.

Causal Evidence that Language Models use Confidence to Drive Behavior Measuring short-form factuality in large language models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.701288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3c8e1160-e5ab-45d5-8497-e068c2e1bf4f · outbound

This paper cites Characterizing LLM Abstention Behavior in Science QA with Context Perturbations.

Causal Evidence that Language Models use Confidence to Drive Behavior Characterizing LLM Abstention Behavior in Science QA with Context Perturbations

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.654008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 707623d4-48dd-472a-9185-5aafe577e0ac · outbound

This paper cites Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs.

Causal Evidence that Language Models use Confidence to Drive Behavior Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:44:05.672847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8eda5362-cc03-4d7c-b667-aec3e623f73a · outbound

This paper cites Mitigating LLM Hallucinations via Conformal Abstention.

Causal Evidence that Language Models use Confidence to Drive Behavior Mitigating LLM Hallucinations via Conformal Abstention

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-21T09:44:05.712207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ebf0cbaa-2f24-40b2-b25f-082e3e491f97 · outbound

This paper cites R-tuning: Instructing large language models to say ‘i don’t know’.

Causal Evidence that Language Models use Confidence to Drive Behavior R-tuning: Instructing large language models to say ‘i don’t know’

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:06.016675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b2d9cf28-e035-4d59-a349-365a5aeb5922 · outbound

This paper cites DK carried out the experiments and analysis with input from ND.

Causal Evidence that Language Models use Confidence to Drive Behavior DK carried out the experiments and analysis with input from ND

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:06.018937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9ede41af-6b12-411e-ad3d-2a945c873704 · outbound

This paper cites baked in.

Causal Evidence that Language Models use Confidence to Drive Behavior baked in

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:06.005408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 37764020-a0dd-44ef-9e92-3e193a6a1f14 · outbound

This paper cites an unresolved cited work.

Causal Evidence that Language Models use Confidence to Drive Behavior Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-21T09:44:06.009862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 88975484-71b7-4ea6-a4e1-beeea7248dcc · outbound

This paper cites T:χ 2(1) = 391.82, p < .001 Threshold + Difficulty 9824.5 0.355 – Full (T + Confidence + Difficulty) 9544.4 0.374 vs.

Causal Evidence that Language Models use Confidence to Drive Behavior T:χ 2(1) = 391.82, p < .001 Threshold + Difficulty 9824.5 0.355 – Full (T + Confidence + Difficulty) 9544.4 0.374 vs

Reference 30

Resolution: malformed identifier; raw_fallback, observed 2026-05-21T09:44:06.002412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0dc13d63-fcf6-41b2-b34c-b98129595c30 · outbound

This paper cites T:χ 2(1) = 445.93, p < .001 Threshold + Difficulty 13540.5 0.109 – Full (T + Confidence + Difficulty) 13206.1 0.132 vs.

Causal Evidence that Language Models use Confidence to Drive Behavior T:χ 2(1) = 445.93, p < .001 Threshold + Difficulty 13540.5 0.109 – Full (T + Confidence + Difficulty) 13206.1 0.132 vs

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:44:06.007471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation c486f0ec-ae54-4a30-9aa5-31f3b2cd4f39 · inbound

Reported Confidence in LLMs Tracks Commitment More Than Correctness cites this paper.

Reported Confidence in LLMs Tracks Commitment More Than Correctness Causal Evidence that Language Models use Confidence to Drive Behavior

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-30T08:04:28.793227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.