Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

Yanbo Wang, Minzheng Wang, Jian Liang, Lu Wang +2 more

Published

Feb 14, 2026

Citations

0

Trust level

Low

Usefulness score

40/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jun 29, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Coding Pairwise Preference

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

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
40/100
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

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and utility. However, prevailing alignment strategies typically construct CoT training data with explicit safety rules via context distillation. This approach inadvertently limits reasoning capabilities by creating a rigid association between rule memorization and refusal. To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning~(ASCL) framework to improve the reasoning given proper context. ASCL formulates safety alignment as a multi-turn tool-use process, empowering the model to autonomously decide when to consult safety rules and how to generate the ongoing reasoning. Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization~(IFPO) to rebalance advantage estimates. By decoupling rule retrieval and subsequent reasoning, our method achieves higher overall performance compared to baselines. Our code is publicly available at https://github.com/ybwang119/ASCL.

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

partial

Pairwise Preference

Directly usable for protocol triage.

"While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures."

Quality Controls

missing

Not reported

No explicit QC controls found.

"While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures."

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
Yes
Feedback types
Pairwise Preference
Rater population
Not reported
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

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures.

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

Key takeaways

  • While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures.
  • For safety alignment, the core challenge lies in the inherent trade-off between safety and utility.
  • However, prevailing alignment strategies typically construct CoT training data with explicit safety rules via context distillation.

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

Pairwise preference evaluation

Contribution summary

  • While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures.
  • To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning~(ASCL) framework to improve the reasoning given proper context.
  • Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization~(IFPO) to rebalance advantage estimates.

Why it matters for eval

  • To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning~(ASCL) framework to improve the reasoning given proper context.
  • Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization~(IFPO) to rebalance advantage estimates.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • 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.