Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance

Stefan Bühler, David Exler, Markus Reischl, Mark Schutera

Published

Oct 5, 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

Oct 5, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Multi Agent

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

A secondary eval reference to pair with stronger protocol papers.

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
Detected
Eval setup described
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

Are language models compliant with user instructions? A model that always complies can be stopped but also exploited, while one that always resists can be neither exploited nor stopped. We contribute an open two-probe benchmark that can place any language model on this spectrum. In the active probe, a user instructs the model to act and accept a lower payoff, which measures exploitability. In the passive probe, the user instructs it to wait and give up a higher payoff, which measures stoppability. The two compliance rates combine into a compliance index $κ$. Applied to twelve language models, the benchmark shows that seven mostly follow the instruction in both probes and justify their action by pointing to the instruction. Only Claude Sonnet-4.6 and Claude Opus-4.7 can be stopped without being exploitable, Claude Opus-4.6 and GPT-5-mini resist both instructions, and no model is exploitable but unstoppable. Knowing where a language model sits on the compliance index $κ$ matters for human operators and for multi-agent systems, whether distributed or orchestrated.

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.

"Are language models compliant with user instructions?"

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Are language models compliant with user instructions?"

Quality Controls

missing

Not reported

No explicit QC controls found.

"Are language models compliant with user instructions?"

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Are language models compliant with user instructions?"

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Are language models compliant with user instructions?"

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
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
Multi Agent
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Are language models compliant with user instructions?

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

Key takeaways

  • Are language models compliant with user instructions?
  • A model that always complies can be stopped but also exploited, while one that always resists can be neither exploited nor stopped.
  • We contribute an open two-probe benchmark that can place any language model on this spectrum.

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

  • We contribute an open two-probe benchmark that can place any language model on this spectrum.
  • Applied to twelve language models, the benchmark shows that seven mostly follow the instruction in both probes and justify their action by pointing to the instruction.
  • Knowing where a language model sits on the compliance index κ matters for human operators and for multi-agent systems, whether distributed or orchestrated.

Why it matters for eval

  • We contribute an open two-probe benchmark that can place any language model on this spectrum.
  • Applied to twelve language models, the benchmark shows that seven mostly follow the instruction in both probes and justify their action by pointing to the instruction.

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.