Skip to content
← Back to explorer

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning

Jyotin Goel, Souvik Maji, Pratik Mazumder · Feb 19, 2026 · Citations: 0

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

Abstract

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a trade-off between safety and utility. We introduce a training framework that adapts regularization in response to safety risk, enabling models to remain aligned throughout fine-tuning. To estimate safety risk at training time, we explore two distinct approaches: a judge-based Safety Critic that assigns high-level harm scores to training batches, and an activation-based risk predictor built with a lightweight classifier trained on intermediate model activations to estimate harmful intent. Each approach provides a risk signal that is used to constrain updates deemed higher risk to remain close to a safe reference policy, while lower-risk updates proceed with standard training. We empirically verify that harmful intent signals are predictable from pre-generation activations and that judge scores provide effective high-recall safety guidance. Across multiple model families and attack scenarios, adaptive regularization with either risk estimation approach consistently lowers attack success rate compared to standard fine-tuning, preserves downstream performance, and adds no inference-time cost. This work demonstrates a principled mechanism for maintaining safety without sacrificing utility.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • This paper looks adjacent to evaluation work, but not like a strong protocol reference.
  • The available metadata is too thin to trust this as a primary source.

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence: Low

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

Quality Controls

missing

Not reported

No explicit QC controls found.

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

Reported Metrics

partial

Recall, Success rate, Cost, Jailbreak success rate

Useful for evaluation criteria comparison.

Rater Population

missing

Unknown

Rater source not explicitly reported.

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Low
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

recallsuccess ratecostjailbreak success rate

Research Brief

Deterministic synthesis

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 10:33 AM · Grounded in abstract + metadata only

Key Takeaways

  • Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates.
  • Existing defenses often offer limited protection or force a trade-off between safety and utility.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (recall, success rate, cost).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates.
  • Existing defenses often offer limited protection or force a trade-off between safety and utility.
  • We introduce a training framework that adapts regularization in response to safety risk, enabling models to remain aligned throughout fine-tuning.

Why It Matters For Eval

  • Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates.
  • We introduce a training framework that adapts regularization in response to safety risk, enabling models to remain aligned throughout fine-tuning.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: recall, success rate, cost, jailbreak success rate

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.