Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJan 11, 2026Vancouver

Curvature-aware sycophancy reduction

Shovon Biswas · Team curvature

Submitted to AI Manipulation Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Curvature-aware sycophancy reduction

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

How does sycophancy, as opposed to truthful behavior, shape the loss landscape? To investigate this question, we construct a simple math_sycophantic dataset consisting of sycophantic, incorrect question–answer pairs involving basic arithmetic manipulations. We run this dataset through Qwen‑0.5B‑Instruct and compute the Kronecker‑factored approximate curvature (KFAC) for two settings: Case A, where the model is given a question paired with a sycophantic incorrect answer, and Case B, where the model is given the same question paired with the correct answer. We find that the resulting KFAC matrices for Cases A and B are able to distinguish between the two tasks for this simple dataset. Building on this observation, we introduce a simple weight‑editing method that leverages both activation and gradient correlation matrices to modify the middle linear layers of the base model, and produce steered variants. These steered models exhibit measurably reduced sycophancy compared to the base model.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. This project investigates whether sycophancy is represented in the loss landscape by using curvature analysis and weight-projection editing. Examining sycophancy in this way is a novel approach and the experimental set-up is clean and clearly defined. The authors provide sufficient detail to understand the process and ground the research in previous works. They acknowledge that the work is exploratory, but the claims made in the conclusion may be a little too optimistic about the ability to apply this to more realistic datasets.

    The write-up and presentation of results are clear. I feel that the project would benefit from a closer examination of the claim that "reducing sycophancy should increase truthfulness” as it is based on a narrow definition of sycophancy that presupposes a “correct answer”.

  2. I like the fundamental attempt to isolate behaviors at a weights level. Ambitious project for a hackathon with theory, finetuning, and evaluation all in one.

    However, left with multiple questions:

    1. KFAC assumptions: The link between KFAC specifically and the assumptions about sycophancy isn't clear. It's not obvious to me sycophancy even specifically exists as a distinct measurable concept as the hypothesis suggests. This seems to be a load-bearing assumption - that sycophancy exists in a certain way in the loss landscape - which I'm not sure this data proves/falsifies/isolates specifically, versus other factors like affirm/deny, general entropy, etc. This is the case with any project involving dense LLMs, but here you are specifically proposing an observable architectural mechanism.

    2. Model size: Yes, the model is small which limits conclusions and adds noise, but fundamentally it would've been hard to demand a large theoretical finetuning run over a weekend.

    Would've been a 5 if the results were tighter with causal ablations.

    Read full reviewShow less

Cite this project

@misc{biswas2026curvatureaware,
  title = {{Curvature-aware sycophancy reduction}},
  author = {Shovon Biswas},
  year = {2026},
  month = jan,
  note = {Submitted to AI Manipulation Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/curvatureaware-sycophancy-reduction-ucc4}},
  url = {https://apartresearch.com/sprints/projects/curvatureaware-sycophancy-reduction-ucc4}
}

More from AI Manipulation Hackathon

All 70 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026