Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-16T04:28:15.771544Z
Paper Citation Record · LEDGER
On the Limitations of Steering in Language Model Alignment
As of 22 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 0 inbound Pith citation observations for arXiv:2505.01162.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
11 of 11 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved10
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation c05723da-31b9-471a-98b9-1656e057ca42 · outbound
This paper cites doi: 10.1162/coli a 00524.
On the Limitations of Steering in Language Model Alignment doi: 10.1162/coli a 00524
Reference 2
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-16T04:28:15.711620Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4515535e-a1c2-4bb0-b119-0f5fa459dc6c · outbound
This paper cites Inference-Time Intervention: Eliciting Truthful Answers from a Language Model.
On the Limitations of Steering in Language Model Alignment Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.717431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1192d930-f012-4348-9a68-32f66b94a243 · outbound
This paper cites GPT-4 Technical Report.
On the Limitations of Steering in Language Model Alignment GPT-4 Technical Report
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.733955Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 398dc27f-9d53-4db4-8c3a-33d8e5365e88 · outbound
This paper cites Steering Llama 2 via Contrastive Activation Addition.
On the Limitations of Steering in Language Model Alignment Steering Llama 2 via Contrastive Activation Addition
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.740063Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 241c311f-3d57-4722-8623-ca7a38771e41 · outbound
This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.
On the Limitations of Steering in Language Model Alignment Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.746137Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8b7f8c90-dd6e-4271-94a0-89c99fd1d291 · outbound
This paper cites Linear Representations of Sentiment in Large Language Models.
On the Limitations of Steering in Language Model Alignment Linear Representations of Sentiment in Large Language Models
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.759209Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f22ec94c-9dbf-4981-86c2-00301e31649c · outbound
This paper cites Steering Language Models With Activation Engineering.
On the Limitations of Steering in Language Model Alignment Steering Language Models With Activation Engineering
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.765005Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1567efb-18eb-43b9-914e-45dd97395275 · outbound
This paper cites Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability.
On the Limitations of Steering in Language Model Alignment Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.771544Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3da1400d-4fe1-460d-b28c-821007d36f2a · outbound
This paper cites Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism.
On the Limitations of Steering in Language Model Alignment Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.727690Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 26caa330-1b9d-4c81-bdb1-de15e44dad8a · outbound
This paper cites Refusal in Language Models Is Mediated by a Single Direction.
On the Limitations of Steering in Language Model Alignment Refusal in Language Models Is Mediated by a Single Direction
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.705041Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7e38e289-cb8c-403c-bb84-12372feb1afe · outbound
This paper cites Analyzing the Generalization and Reliability of Steering Vectors.
On the Limitations of Steering in Language Model Alignment Analyzing the Generalization and Reliability of Steering Vectors
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:28:15.752786Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.