Paper Citation Record · LEDGER

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization

As of 8 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2602.07639.

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

pith.paper-citation-record.v1
2602.07639 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:36:16.874372Z

measured 35 of 35 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 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

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7240cdfd-c4af-4deb-9c66-6c04b355a975 · outbound

This paper cites Personalized steering of large language models: Versatile steering vectors through bi-directional preference optimization.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Personalized steering of large language models: Versatile steering vectors through bi-directional preference optimization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.728598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f526a62-9c85-4d06-b854-5d11ebc17d8e · outbound

This paper cites Livehint overview.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Livehint overview

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.734007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b586b3-5f83-4d07-8494-80b7ca981eb8 · outbound

This paper cites Persona Vectors: Monitoring and Controlling Character Traits in Language Models.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.738475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 429c47b6-50d6-4203-ac43-4b45bd1b9173 · outbound

This paper cites From problem-solving to teaching problem-solving: Aligning LLMs with pedagogy using reinforcement learning.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization From problem-solving to teaching problem-solving: Aligning LLMs with pedagogy using reinforcement learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.743516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57a5c8e3-8e93-414d-8062-f3bfb26197ed · outbound

This paper cites Dynamics of affective states during complex learning.Learning and Instruction, 22(2):145–157, 2012.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Dynamics of affective states during complex learning.Learning and Instruction, 22(2):145–157, 2012

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.747974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de0bd0fd-839e-476a-900a-e5751de1addc · outbound

This paper cites Gemini.https://deepmind.google/technologies/gemini/, 2023.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Gemini.https://deepmind.google/technologies/gemini/, 2023

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.752692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cbc8a82-9e8f-4bb8-a3dc-992f53ed65dd · outbound

This paper cites Collaborative dialogue patterns in naturalistic one-to-one tutoring.Applied cognitive psychology, 9(6):495–522, 1995.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Collaborative dialogue patterns in naturalistic one-to-one tutoring.Applied cognitive psychology, 9(6):495–522, 1995

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.757823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f446444-4b6c-4925-970e-4c5528a1181e · outbound

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

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization LoRA: Low-rank adaptation of large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.761916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575e5a62-c974-4c81-839b-f1c9df96fef3 · outbound

This paper cites Supercharge your teaching experience with khanmigo.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Supercharge your teaching experience with khanmigo

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.766030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8add7bc-47f7-4cf1-97f2-90d4b1007c60 · outbound

This paper cites Prometheus 2: An open source language model specialized in evaluating other language models.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Prometheus 2: An open source language model specialized in evaluating other language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.770281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dd2412b-506c-4acd-9e24-4ccbd336c619 · outbound

This paper cites Preserving diversity in supervised fine-tuning of large language models.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Preserving diversity in supervised fine-tuning of large language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.774244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1809f6ff-a290-4556-aa5b-205d8f8243b0 · outbound

This paper cites Rouge: A package for automatic evaluation of summaries.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Rouge: A package for automatic evaluation of summaries

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.778272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f8f33b4-441a-4609-96bd-ba88040950d3 · outbound

This paper cites In-context vectors: making in context learning more effective and controllable through latent space steering.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization In-context vectors: making in context learning more effective and controllable through latent space steering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.782582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6969d727-2aae-4b0e-bdd7-4676c7c0227c · outbound

This paper cites Personality-aware student simulation for conver- sational intelligent tutoring systems.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Personality-aware student simulation for conver- sational intelligent tutoring systems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.786625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ef420a-8626-4c06-a6d7-7eb58a4e9a5c · outbound

This paper cites Training Millions of Personalized Dialogue Agents.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Training Millions of Personalized Dialogue Agents

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.790743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c4312c-ddd1-4421-a2a2-e136478e2155 · outbound

This paper cites An introduction to the five-factor model and its applications.Journal of personality, 60(2):175–215, 1992.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization An introduction to the five-factor model and its applications.Journal of personality, 60(2):175–215, 1992

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.795240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 683a5c95-72b0-4c42-8ecb-4f1dade1f4f6 · outbound

This paper cites Chatgpt.https://chat.openai.com, 2023.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Chatgpt.https://chat.openai.com, 2023

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.799454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1490bb5-9de1-4c3b-9403-39547ddf3b4a · outbound

This paper cites Autotutor meets large language models: A language model tutor with rich pedagogy and guardrails.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Autotutor meets large language models: A language model tutor with rich pedagogy and guardrails

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.803346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05dffd7-f7c6-4220-a556-e00a476389f6 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Bleu: a method for automatic evaluation of machine translation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.807398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43919082-6dce-44c3-a614-2d9ecc8c9a28 · outbound

This paper cites Towards the pedagogical steering of large language models for tutoring: A case study with modeling productive failure.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Towards the pedagogical steering of large language models for tutoring: A case study with modeling productive failure

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.811509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceab6816-7618-48e6-a010-53e030a105c5 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.815863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 328f22da-27c8-46ff-ad14-d27cbb36dab7 · outbound

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

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Sentence-BERT: Sentence embeddings using Siamese BERT-networks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.820124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fdb9051-5a22-4717-a118-9a66cbdb4708 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Steering llama 2 via contrastive activation addition

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.824290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7b60c18-6f28-43ed-91b3-f3fdf177506a · outbound

This paper cites Principles of instruction: Research-based strategies that all teachers should know.American educator, 36(1):12, 2012.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Principles of instruction: Research-based strategies that all teachers should know.American educator, 36(1):12, 2012

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.828314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 054bca29-34b1-4ca4-adc2-cee49134d3ca · outbound

This paper cites Training llm-based tutors to improve student learning outcomes in dialogues.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Training llm-based tutors to improve student learning outcomes in dialogues

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.832483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d021fd10-23e6-414f-9b40-84708316fba6 · outbound

This paper cites Improving the validity of automatically generated feedback via reinforcement learning.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Improving the validity of automatically generated feedback via reinforcement learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.836576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 072c4dc6-ccf7-47c8-860e-918b60da081d · outbound

This paper cites Personality traits in large language models.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Personality traits in large language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.840755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd132c3-96dd-48d0-a63b-8053dcf4b906 · outbound

This paper cites Focus on formative feedback.Review of educational research, 78(1):153–189, 2008.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Focus on formative feedback.Review of educational research, 78(1):153–189, 2008

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.844806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0040dac6-439e-417b-90d9-d28dbc6636ef · outbound

This paper cites Pedagogical alignment of large language models.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Pedagogical alignment of large language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.849167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f86cf4-e8cb-41cc-aba4-4f524cde4ed6 · outbound

This paper cites The use of worked examples as a substitute for problem solving in learning algebra.Cognition and instruction, 2(1):59–89, 1985.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization The use of worked examples as a substitute for problem solving in learning algebra.Cognition and instruction, 2(1):59–89, 1985

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.853586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 216764a7-1804-4d8c-b85d-6ef736faed5d · outbound

This paper cites Steering Language Models With Activation Engineering.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Steering Language Models With Activation Engineering

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.857685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f9c16ad-286d-4279-9cc4-970034072826 · outbound

This paper cites Trojan activation attack: Red-teaming large language models using steering vectors for safety-alignment.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization Trojan activation attack: Red-teaming large language models using steering vectors for safety-alignment

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.862089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c285a8d-1244-4f95-b975-7d9f3d520ef3 · outbound

This paper cites The role of tutoring in problem solving.Journal of child psychology and psychiatry, 17(2):89–100, 1976.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization The role of tutoring in problem solving.Journal of child psychology and psychiatry, 17(2):89–100, 1976

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.866305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4ef823a-4e2d-4711-9ddd-1f53915179be · outbound

This paper cites PIIvot: A lightweight NLP anonymization framework for question-anchored tutoring dialogues.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization PIIvot: A lightweight NLP anonymization framework for question-anchored tutoring dialogues

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.870443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5058c9c3-8e21-44a0-8bc7-e88953d6c7d9 · outbound

This paper cites SPL: A Socratic Playground for Learning Powered by Large Language Model.

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization SPL: A Socratic Playground for Learning Powered by Large Language Model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:16.874372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.