Paper Citation Record · LEDGER

Differentially Private Steering for Large Language Model Alignment

As of 14 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 2 inbound Pith citation observations for arXiv:2501.18532.

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

pith.paper-citation-record.v1
2501.18532 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T23:12:56.339661Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:47:29.370583Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T05:47:35.208989Z

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy8
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 64854c9e-81d5-4aec-a2f3-60e54154a677 · outbound

This paper cites an unresolved cited work.

Differentially Private Steering for Large Language Model Alignment Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-09T23:12:56.575495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 499e32fc-8b40-4089-8c1c-2186a8279d70 · outbound

This paper cites Again, we observe a clear trend of decrease in performance with larger clipping thresholds (Figure 5).

Differentially Private Steering for Large Language Model Alignment Again, we observe a clear trend of decrease in performance with larger clipping thresholds (Figure 5)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.593136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e43457bb-3789-469c-9a2c-552f4d62d0b2 · outbound

This paper cites Adversary instantiation: Lower bounds for differentially private machine learning.

Differentially Private Steering for Large Language Model Alignment Adversary instantiation: Lower bounds for differentially private machine learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.689880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9c429acb-3e2f-4989-a6ae-ff2976e6fa72 · outbound

This paper cites The Geometry of Categorical and Hierarchical Concepts in Large Language Models.

Differentially Private Steering for Large Language Model Alignment The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.257569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 192b2961-c928-47f7-861d-87ba0fceeb0a · outbound

This paper cites NormFormer: Improved Transformer Pretraining with Extra Normalization.

Differentially Private Steering for Large Language Model Alignment NormFormer: Improved Transformer Pretraining with Extra Normalization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.267577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a313f1-20f3-4ec7-9b9e-904380972366 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Differentially Private Steering for Large Language Model Alignment Gemma: Open Models Based on Gemini Research and Technology

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.273340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 188669a1-c25a-4dd0-9c78-ec3e277229f3 · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

Differentially Private Steering for Large Language Model Alignment Linear Representations of Sentiment in Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.281407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12cd1a94-4846-46cb-b092-767d1c014332 · outbound

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

Differentially Private Steering for Large Language Model Alignment Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.287486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986026a3-faf7-4d1d-9426-b725b8b03c2c · outbound

This paper cites Steering Language Models With Activation Engineering.

Differentially Private Steering for Large Language Model Alignment Steering Language Models With Activation Engineering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.293546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 264ad356-3b63-485b-8c02-9dbaa2b8cddf · outbound

This paper cites Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods.

Differentially Private Steering for Large Language Model Alignment Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.298735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f22e3ea-bfe3-4061-a993-09a2cfe03604 · outbound

This paper cites Qwen2 Technical Report.

Differentially Private Steering for Large Language Model Alignment Qwen2 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.304006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9899a020-7bc7-4d92-83cf-83c29451de60 · outbound

This paper cites Analyzing information leakage of updates to natural language models.

Differentially Private Steering for Large Language Model Alignment Analyzing information leakage of updates to natural language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.652144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2d742137-998e-43fc-a265-1869a9ca056b · outbound

This paper cites I am a 32 year old liberal politician from San Francisco.

Differentially Private Steering for Large Language Model Alignment I am a 32 year old liberal politician from San Francisco

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.629441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 39e126da-09b5-41ca-8bbd-8ca7b6e15a1c · outbound

This paper cites an unresolved cited work.

Differentially Private Steering for Large Language Model Alignment Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-09T23:12:56.609510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 18de7a67-8ed0-4ad0-95df-8af615a38daa · outbound

This paper cites an unresolved cited work.

Differentially Private Steering for Large Language Model Alignment Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-09T23:12:56.558271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f3c11820-9c49-4afa-be00-c6f957d2368d · outbound

This paper cites GPT-4 Technical Report.

Differentially Private Steering for Large Language Model Alignment GPT-4 Technical Report

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.222316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74625b04-474b-4809-a3b4-aba9e1c3452b · outbound

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

Differentially Private Steering for Large Language Model Alignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.314374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff066f38-1c00-4073-bfe3-5e86e6de0a7f · outbound

This paper cites Are large pre-trained language models leaking your personal information? In Findings of the Association for Computational Linguistics: EMNLP, pp.

Differentially Private Steering for Large Language Model Alignment Are large pre-trained language models leaking your personal information? In Findings of the Association for Computational Linguistics: EMNLP, pp

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.723937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 137f207d-3c1b-4c93-9d84-1d2cb5f27fad · outbound

This paper cites Flocks of stochastic parrots: Differentially private prompt learning for large language models.

Differentially Private Steering for Large Language Model Alignment Flocks of stochastic parrots: Differentially private prompt learning for large language models

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.742787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f3457c5-8dca-4742-9bf4-bda1dd0ada4a · outbound

This paper cites Adversarial Attacks on Image Generation With Made-Up Words.

Differentially Private Steering for Large Language Model Alignment Adversarial Attacks on Image Generation With Made-Up Words

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T23:12:56.245717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 474bd067-b56b-4cf7-a936-b21bc67d4f55 · outbound

This paper cites Confident adaptive language modeling.

Differentially Private Steering for Large Language Model Alignment Confident adaptive language modeling

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.672971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation caeda88e-a55d-43f5-9bbb-8b5f2e22a832 · outbound

This paper cites How good are llms at out-of-distribution detection? In Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING) , pp.

Differentially Private Steering for Large Language Model Alignment How good are llms at out-of-distribution detection? In Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING) , pp

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T23:12:56.706748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation ba73bc6b-a27c-4557-8f46-615cafa236ac · inbound

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models cites this paper.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differentially Private Steering for Large Language Model Alignment

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:47:35.261379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 36343730-8574-4536-bc14-02e2838ef3c8 · inbound

Probabilistic Concept-Aware Steering for Trustworthy LLM Inference cites this paper.

Probabilistic Concept-Aware Steering for Trustworthy LLM Inference Differentially Private Steering for Large Language Model Alignment

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T13:56:47.814089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.