Paper Citation Record · LEDGER

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions

As of 9 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2607.08776.

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

pith.paper-citation-record.v1
2607.08776 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T08:04:29.580811Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cbb8f483-f147-468b-89b7-a361c91ac52d · outbound

This paper cites Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23064cd9-97c1-456f-830d-0909cf78fd81 · outbound

This paper cites Defining and Extracting generalizable interaction primitives from DNNs.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Defining and Extracting generalizable interaction primitives from DNNs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2af95aa-b8f2-4bd9-872c-b89e90a2c593 · outbound

This paper cites E., et al.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions E., et al

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c571ff5-0f5c-4962-9b61-6debd4cd2678 · outbound

This paper cites Feature Removal Is a Unifying Principle for Model Explanation Methods.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Feature Removal Is a Unifying Principle for Model Explanation Methods

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9520a6fe-a9c3-49c7-a007-c1b16dded02a · outbound

This paper cites MiniPLM: Knowledge Distillation for Pre-Training Language Models.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions MiniPLM: Knowledge Distillation for Pre-Training Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 808cb2df-5f4e-44a8-948d-e62519d56e86 · outbound

This paper cites Tinybert: Distilling bert for natural language understanding.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Tinybert: Distilling bert for natural language understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc63a30-df2e-4bb3-81d0-17e3db19673a · outbound

This paper cites Promptkd: Distilling student-friendly knowledge for generative language mod- els via prompt tuning.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Promptkd: Distilling student-friendly knowledge for generative language mod- els via prompt tuning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d530c7d-b2b9-4536-959c-edf893895c10 · outbound

This paper cites and Rush, A.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions and Rush, A

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bad64279-fd00-4efc-8faa-acb9f3eab34a · outbound

This paper cites DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a1af472-0722-4e98-a533-ee8c97acfef4 · outbound

This paper cites Homodistil: Homotopic task-agnostic distillation of pre-trained transformers.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Homodistil: Homotopic task-agnostic distillation of pre-trained transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35d0d52-486b-4665-ace9-f9455050a7c0 · outbound

This paper cites FitNets: Hints for Thin Deep Nets.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions FitNets: Hints for Thin Deep Nets

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669e01dd-a6a3-4446-a985-ef50838c7d4e · outbound

This paper cites Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df4220a-fcfd-458d-a18d-38f4bbf613db · outbound

This paper cites Patient knowledge distillation for bert model compression.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Patient knowledge distillation for bert model compression

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 947e009f-c602-43e8-aa69-cfb15e10d8db · outbound

This paper cites The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a22e9749-f16f-43e0-b041-7f9621bc0533 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions LLaMA: Open and Efficient Foundation Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d134a0c-f3a2-4dc5-a0c0-3993ca258be5 · outbound

This paper cites doi: 10.18653/v1/ 2023.acl-long.605.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions doi: 10.18653/v1/ 2023.acl-long.605

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56d3916f-8f4b-4444-a377-75a32af5c37d · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions OPT: Open Pre-trained Transformer Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c205735-809e-433b-a5fc-22345eec3cac · outbound

This paper cites More recent approaches have explored contrastive representation distillation (Tian et al.,.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions More recent approaches have explored contrastive representation distillation (Tian et al.,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a094d1f7-b14a-4b0b-92d4-6316d1403e80 · outbound

This paper cites Others have proposed homotopic distillation for pre-trained transformers (Liang et al., 2023a) or utilized Wasserstein distance to match feature distributions (Lv et al., 2024).

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Others have proposed homotopic distillation for pre-trained transformers (Liang et al., 2023a) or utilized Wasserstein distance to match feature distributions (Lv et al., 2024)

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ab3001-e2e3-499d-acb8-b8eb6c57f328 · outbound

This paper cites an unresolved cited work.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc52fc3c-44db-48b7-8a8a-3a4dc0ba1b5e · outbound

This paper cites Furthermore, distillation is applied to critical safety tasks, such as the detection and mitigation of hallucinations in large language models (Zhou et al., 2025).

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Furthermore, distillation is applied to critical safety tasks, such as the detection and mitigation of hallucinations in large language models (Zhou et al., 2025)

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 260d0408-11dd-4cb2-b917-d8af61942dea · outbound

This paper cites The selection of a masking approach is complex, as each method has its weakness.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions The selection of a masking approach is complex, as each method has its weakness

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b74683c-5585-4260-9466-d960820ae9a0 · outbound

This paper cites He is a green hand,.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions He is a green hand,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce082a7c-3315-41f7-955e-829bbb15241f · outbound

This paper cites Instruction.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Instruction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f88568a-474c-464f-9001-5ac0ab239b10 · outbound

This paper cites It utilizes a mixed dataset and proposes an adaptive off-policy method to selectively incorporate SGOs based on validation loss, thereby filtering out noisy generated data.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions It utilizes a mixed dataset and proposes an adaptive off-policy method to selectively incorporate SGOs based on validation loss, thereby filtering out noisy generated data

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d470f26-ab0b-41fc-a079-c70bf172b2ef · outbound

This paper cites Instruction.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Instruction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2465bb3-b045-4a7e-a01d-8b3695f729bd · outbound

This paper cites [[rating]].

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions [[rating]]

Reference 27

Resolution: malformed identifier; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f587f00-5cae-42d4-a1bb-80e52d936c3c · outbound

This paper cites What", "is.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions What", "is

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3a62f3-5c98-45a0-bd9c-5f7fd3ac9906 · outbound

This paper cites an unresolved cited work.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Unresolved cited work

Reference 29

Resolution: malformed identifier; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6cefee7-d6d4-4898-a709-a3445d720c64 · outbound

This paper cites Table 7.Instruction-following cases from thedatabricks-dolly-15kdataset.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Table 7.Instruction-following cases from thedatabricks-dolly-15kdataset

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58683096-75be-4e0e-8059-f610b1d9727a · outbound

This paper cites Patrick’s.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions Patrick’s

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 676d3e1a-24d4-41b4-bdea-d2c9692c079c · outbound

This paper cites w/ CIP Claughaun won the 57th edition of the Limerick Senior hurling championship after defeating St.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions w/ CIP Claughaun won the 57th edition of the Limerick Senior hurling championship after defeating St

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e90b86a5-bb4e-442f-99e3-8f8cc6d75e96 · outbound

This paper cites MiniLLM w/o CIP Claughaun won the 63rd staging an went on to win the next four senior hurling championships.

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions MiniLLM w/o CIP Claughaun won the 63rd staging an went on to win the next four senior hurling championships

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T08:04:29.580811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.