Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Interactive Program Induction with Language Model Priors

Robin Shing Moon Chan, Ryan Cotterell

Published

Nov 13, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 13, 2026

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

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

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.

Abstract

Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples. This paradigm broadens programming access by letting users demonstrate the rule-based behavior they want to apply to unseen data, instead of having to implement it themselves. However, recovering a program from finite input-output examples is fundamentally ambiguous, as a finite set of input-output examples is theoretically consistent with infinitely many programs whose output diverges on unseen inputs. We view this problem from a Bayesian perspective, where, given a prior $p^0$ over programs, identifying the target program means concentrating posterior probability mass on it by observing additional input-output examples. In the interactive program induction setting, the learner chooses maximally informative inputs and queries an oracle, such as the user, for their outputs. We derive a greedy query-selection algorithm and show that it terminates after $\mathcal{O}(\frac{1}γ\log 1/p^0(f^\star))$ informative oracle queries, and returns the target program $f^\star$ up to approximate equivalence when no other class outweighs it under the prior. The algorithm uses a language model as the prior under a PAC-style relaxation of program equivalence, where the query-selection objective is estimated using importance sampling. On the CodeARC benchmark, the algorithm improves accuracy over the LM only agent by up to 22 percentage points while observing up to 10.5 fewer input-output examples.

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.

"Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"On the CodeARC benchmark, the algorithm improves accuracy over the LM only agent by up to 22 percentage points while observing up to 10.5 fewer input-output examples."

Benchmarks and datasets

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

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples.

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

Key takeaways

  • Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples.
  • This paradigm broadens programming access by letting users demonstrate the rule-based behavior they want to apply to unseen data, instead of having to implement it themselves.
  • However, recovering a program from finite input-output examples is fundamentally ambiguous, as a finite set of input-output examples is theoretically consistent with infinitely many programs whose output diverges on unseen inputs.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) 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

  • Program induction refers to the process in which a learner aims to recover a program from a few given input-output examples.
  • This paradigm broadens programming access by letting users demonstrate the rule-based behavior they want to apply to unseen data, instead of having to implement it themselves.

Why it matters for eval

  • On the CodeARC benchmark, the algorithm improves accuracy over the LM only agent by up to 22 percentage points while observing up to 10.5 fewer input-output examples.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • 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

    Detected: accuracy