Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families

Abdul Rafay Syed

Published

Jun 18, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

15% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jun 18, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

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.

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

Best use

Background context only

Use if you need

Background context only.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

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

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
Adjacent candidate

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

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure. We investigate whether this misalignment corresponds to a causally actionable activation-space direction shared across architectures. Across four instruction-tuned model families (Qwen2.5-1.5B, Gemma-2-2B, Llama-3.2-1B, Ministral-3-3B) finetuned identically, a difference-in-means direction achieves 99.6% separation of aligned and misaligned activations at each model's final layer. Causal steering by subtracting this direction reduces code spillover by 21-51 points, while a secure-code control confirms content specificity. Cross-architecture transfer via ridge regression maps yields large behavioral suppression (up to 46 points) but fails specificity controls as random and orthogonal directions perform comparably. We identify a two-tier specificity structure: within-model directions are causally specific and actionable; cross-model directions are causally real but non-specific. An asymmetric transfer topology emerges, with Gemma and Qwen acting as geometric donors and Llama as a receiver. These findings define the limits of linear cross-architecture correction and recommend within-model probing for auditing.

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.

"Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure."

Benchmarks and datasets

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

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Scalar (inferred)
Expertise required
Coding
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure.
  • We investigate whether this misalignment corresponds to a causally actionable activation-space direction shared across architectures.
  • Across four instruction-tuned model families (Qwen2.5-1.5B, Gemma-2-2B, Llama-3.2-1B, Ministral-3-3B) finetuned identically, a difference-in-means direction achieves 99.6% separation of aligned and misaligned activations at each model's final layer.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Across four instruction-tuned model families (Qwen2.5-1.5B, Gemma-2-2B, Llama-3.2-1B, Ministral-3-3B) finetuned identically, a difference-in-means direction achieves 99.6% separation of aligned and misaligned activations at each model's…

Why it matters for eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.