Paper Citation Record · LEDGER

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions

As of 20 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 2 inbound Pith citation observations for arXiv:2509.23782.

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

pith.paper-citation-record.v1
2509.23782 v4

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:43:16.659316Z

measured 40 of 40 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T04:32:31.846587Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T05:44:38.784930Z

Reference resolution

38 of 38 outbound references displayed

verified exact1
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d4861c87-8192-4d0b-b3f9-7c44bdf9b39e · outbound

This paper cites Understanding intermediate layers using linear classifier probes, 2017.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Understanding intermediate layers using linear classifier probes, 2017

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:10.834850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fdcf6f6-aa45-452a-be66-1db39a2491e9 · outbound

This paper cites Refusal in language models is mediated by a single direction.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Refusal in language models is mediated by a single direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:10.991738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32bc3b33-4855-4780-ac24-39eefbe48f88 · outbound

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

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions The internal state of an LLM knows when it ' s lying

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.125807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4dbe1c3-1615-497c-840c-7e3b527c8fd0 · outbound

This paper cites Probing the geometry of truth: Consistency and generalization of truth directions in LLM s across logical transformations and question answering tasks.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Probing the geometry of truth: Consistency and generalization of truth directions in LLM s across logical transformations and question answering tasks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.254749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5cbb389-ec1f-41e0-a528-85b13efbd060 · outbound

This paper cites an unresolved cited work.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.344855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c5363e6-c712-4c37-aa28-cbdd340f86bd · outbound

This paper cites Answer Matching Outperforms Multiple Choice for Language Model Evaluation.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Answer Matching Outperforms Multiple Choice for Language Model Evaluation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.483898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7cd00fa-fa5a-4de1-95df-e54156878fea · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Gonzalez, Ion Stoica, and Eric P

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.584755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6265235-1739-4e7b-b4a7-88de8c1336db · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.694751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6895e65-dd42-46a4-929b-509c7c8bc0b1 · outbound

This paper cites Knowledge neurons in pretrained transformers.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Knowledge neurons in pretrained transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.774755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa81f760-e8e4-4f17-8f7e-2121feb525a4 · outbound

This paper cites Plug and play language models: A simple approach to controlled text generation.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Plug and play language models: A simple approach to controlled text generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:11.954755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb0ef333-e192-411f-9aa1-fae9edeb02cb · outbound

This paper cites In-Context Learning Creates Task Vectors.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions In-Context Learning Creates Task Vectors

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.104751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb4b5cdf-99b3-4f2c-a364-4d2c26d97398 · outbound

This paper cites Measuring massive multitask language understanding.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Measuring massive multitask language understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.266840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d4ef28b-d407-497e-8804-bcffa2d9fc7a · outbound

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

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Lo RA : Low-rank adaptation of large language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.474741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c8bab94-f220-462c-976b-10211c9efe78 · outbound

This paper cites Editing Models with Task Arithmetic.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Editing Models with Task Arithmetic

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.554747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c20cf2e-6896-4ecb-8776-5cd00b577bf0 · outbound

This paper cites Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, Erik Miehling, Pierre Dognin, Manish Nagireddy, and Amit Dhurandhar.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, Erik Miehling, Pierre Dognin, Manish Nagireddy, and Amit Dhurandhar

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.639855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e449c57-2bbf-41e4-a5c8-552fc7727168 · outbound

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

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Inference-time intervention: Eliciting truthful answers from a language model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.724755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfb45d73-c2fc-4ae4-8573-2f0168c57871 · outbound

This paper cites an unresolved cited work.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.824752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd241c84-4760-4714-894c-81c6e1b8090f · outbound

This paper cites Investigating Bias Representations in Llama 2 Chat via Activation Steering.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Investigating Bias Representations in Llama 2 Chat via Activation Steering

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:12.984764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef1facb-36b6-4280-aa62-f53b12ec9d0a · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:13.214435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f9e328-d523-40cf-a968-0143306db352 · outbound

This paper cites Locating and editing factual associations in gpt.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Locating and editing factual associations in gpt

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:13.414745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e949ff8-2c33-4a7a-a8d8-bee0c97f1101 · outbound

This paper cites Introducing gpt-5.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Introducing gpt-5

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:13.554750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 769231bb-d2b5-4585-9799-61887f627ff2 · outbound

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

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions LLM s know more than they show: On the intrinsic representation of LLM hallucinations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:13.676180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f8d6d1-c388-471b-901a-1952b944fca0 · outbound

This paper cites Large language models sensitivity to the order of options in multiple-choice questions.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Large language models sensitivity to the order of options in multiple-choice questions

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:13.894756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05c47a6d-4b5b-49c8-8907-a5480d2c89a6 · outbound

This paper cites Qwen2.5 Technical Report.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Qwen2.5 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:14.064827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8311e3c-ea13-4676-b1a3-10d99d7b1a63 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Steering llama 2 via contrastive activation addition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:14.245491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bb0af7-1ac2-481a-b0e3-9d8bd3a65377 · outbound

This paper cites Layer by layer: Uncovering hidden representations in language models.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Layer by layer: Uncovering hidden representations in language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:14.444798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be4e53b3-807c-4d95-ad07-7ae34df46d9f · outbound

This paper cites Unsupervised real-time hallucination detection based on the internal states of large language models.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Unsupervised real-time hallucination detection based on the internal states of large language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:14.604749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de047cd8-163f-4db8-834e-aef3550c8341 · outbound

This paper cites Challenging BIG -bench tasks and whether chain-of-thought can solve them.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Challenging BIG -bench tasks and whether chain-of-thought can solve them

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:14.784754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2e3c5ee-8a7c-4fc2-a8b9-8080c4ee664a · outbound

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

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:14.974820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7997358-7fa8-421c-95c0-603d15ad6dfe · outbound

This paper cites Steering language models with activation engineering, 2025.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Steering language models with activation engineering, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:15.134753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e4287d-2a93-4639-bea7-5c0ce74d9d53 · outbound

This paper cites FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-04T14:43:27.887348Z

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.

Observation b18fa2fb-756c-40fe-b15a-80ee93c497b5 · outbound

This paper cites Chi, Quoc V.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Chi, Quoc V

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:15.404755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2861dfea-6645-4832-901a-d4f7d7302003 · outbound

This paper cites Large language models are not robust multiple choice selectors.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Large language models are not robust multiple choice selectors

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:15.575227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1724327b-ea3d-412a-899c-f0b9ff65cad1 · outbound

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

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Representation Engineering: A Top-Down Approach to AI Transparency

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:15.684752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acb733d1-9244-48e3-ba78-0aed45ec7483 · outbound

This paper cites write newline.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions write newline

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:15.874752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f902df-2182-40a0-b442-5ef5e894cd62 · outbound

This paper cites @esa (Ref.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions @esa (Ref

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:16.134895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a728661-918c-4066-9d0e-5049b5fe8a3d · outbound

This paper cites an unresolved cited work.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:16.324755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07a60ae9-8d01-490c-8a93-19b8e2ee472b · outbound

This paper cites an unresolved cited work.

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:16.659316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b0fd5d4b-2ae4-4e1d-ab70-815f025a85b4 · inbound

Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs cites this paper.

Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-06-02T03:04:01.145620Z

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.

Observation a16442fd-35b7-4eb5-b923-cc08be8f495a · inbound

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models cites this paper.

Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T04:32:31.846587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.