Human Feedback Types
strongPairwise Preference
Directly usable for protocol triage.
"Reward learning typically assumes the human's input covers everything that matters for the task."
HFEPX · Eval paper review
Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards
Helena Merker, Nick Walker, Andreea Bobu
Published
Oct 15, 2026
Citations
0
Trust level
Moderate
Usefulness score
57/100 (Medium)
Extraction confidence
65% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 15, 2026
Should you rely on this paper?
This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.
Use this for comparison and orientation, not as your only source.
Low-signal caution for protocol decisions
Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.
- The abstract does not clearly name benchmarks or metrics.
Best use
Secondary protocol comparison source
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
The abstract does not clearly name benchmarks or metrics.
Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
57/100
Moderate-confidence candidate
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
Abstract
Reward learning typically assumes the human's input covers everything that matters for the task. In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others. Prior work has shown how the robot can identify which features were poorly supervised directly from its teaching data. But the current solution is to ask the human to try again, putting the burden on someone who already struggled to convey those features. We propose shifting this burden to the robot. Our key insight is that the same information that tells the robot what it doesn't know can help it ask better questions. Preference queries offer a low-effort channel for resolving this uncertainty, but only if the robot knows where to direct them and the human knows what to attend to when answering. We act on this insight in two ways: we build an informed prior that targets preference queries at the features that need resolving, and we accompany each query with an explanation that focuses the human's attention on exactly those features. In simulation, the informed prior beats the standard active preference learning baseline by up to $30.8\%$ in the low-query regime, where reducing human effort matters most. In a user study, the informed prior and explanations each significantly improve reward recovery and amplify each other.
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.
Evaluation Modes
strongSimulation Env
Includes extracted eval setup.
"Reward learning typically assumes the human's input covers everything that matters for the task."
Quality Controls
missingNot reported
No explicit QC controls found.
"Reward learning typically assumes the human's input covers everything that matters for the task."
Benchmarks / Datasets
missingNot extracted
No benchmark anchors detected.
"Reward learning typically assumes the human's input covers everything that matters for the task."
Reported Metrics
missingNot extracted
No metric anchors detected.
"Reward learning typically assumes the human's input covers everything that matters for the task."
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
- General
Evaluation details
- Evaluation modes
- Simulation Env
- Agentic eval
- None
- Quality controls
- Not reported
- Evidence quality
- Moderate
- Use this page as
- Secondary protocol comparison source
Research brief
Metadata summary
Reward learning typically assumes the human's input covers everything that matters for the task.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Key takeaways
- Reward learning typically assumes the human's input covers everything that matters for the task.
- In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others.
- Prior work has shown how the robot can identify which features were poorly supervised directly from its teaching data.
Researcher actions
- Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
- Validate inferred eval signals (Simulation environment) against the full paper.
- 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
- Reward learning typically assumes the human's input covers everything that matters for the task.
- In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others.
- We propose shifting this burden to the robot.
Why it matters for eval
- Reward learning typically assumes the human's input covers everything that matters for the task.
- In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others.
Researcher checklist
-
Human feedback protocol is explicit
Detected: Pairwise Preference
-
Evaluation mode is explicit
Detected: Simulation Env
-
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.