Skip to content
← Back to explorer

Training with Pseudo-Code for Instruction Following

Prince Kumar, Rudra Murthy, Riyaz Bhat, Danish Contractor · May 23, 2025 · Citations: 0

Coding Demonstrations Math
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 11, 2026, 5:21 AM

Recent

Extraction refreshed

Mar 13, 2026, 3:18 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests that models may follow instructions more effectively when they are expressed in pseudo-code rather than natural language. However, writing pseudo-code programs can be tedious, and relying on few-shot demonstrations or inference-time code prompting is often unnatural for non-expert users of LLMs. To overcome these limitations, we propose a training time approach that fine-tunes LLMs using instruction-tuning data augmented with pseudo-code representations of natural language instructions paired with final responses. We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models. Our results show that models trained with pseudo-code follow instructions more reliably, achieving relative gains of 8-21\% on instruction following benchmarks, while largely preserving and in some cases improving performance on mathematical and commonsense reasoning tasks, with an average gain of up to 30\% across all evaluated benchmarks.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction confidence is 0.45 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
  • No benchmark/dataset or metric anchors were extracted.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction confidence is 0.45 (below strong-reference threshold).

Trust level

Low

Eval-Fit Score

40/100 • Low

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

Human Feedback Signal

Detected

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

partial

Demonstrations

Confidence: Low Source: Persisted extraction evidenced

Directly usable for protocol triage.

Evidence snippet: However, writing pseudo-code programs can be tedious, and relying on few-shot demonstrations or inference-time code prompting is often unnatural for non-expert users of LLMs.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved.

Reported Metrics

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No metric anchors detected.

Evidence snippet: Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved.

Rater Population

partial

Mixed

Confidence: Low Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: However, writing pseudo-code programs can be tedious, and relying on few-shot demonstrations or inference-time code prompting is often unnatural for non-expert users of LLMs.

Human Data Lens

  • Uses human feedback: Yes
  • Feedback types: Demonstrations
  • Rater population: Mixed
  • Unit of annotation: Unknown
  • Expertise required: Math, Coding
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.45
  • Flags: ambiguous

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

To overcome these limitations, we propose a training time approach that fine-tunes LLMs using instruction-tuning data augmented with pseudo-code representations of natural language instructions paired with final responses. HFEPX signals include Demonstrations with confidence 0.45. Updated from current HFEPX corpus.

Generated Mar 13, 2026, 3:18 PM · Grounded in abstract + metadata only

Key Takeaways

  • To overcome these limitations, we propose a training time approach that fine-tunes LLMs using instruction-tuning data augmented with pseudo-code representations of natural…
  • We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models.

Researcher Actions

  • Compare its human-feedback setup against pairwise and rubric hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Verify metric definitions before comparing against your eval pipeline.

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • To overcome these limitations, we propose a training time approach that fine-tunes LLMs using instruction-tuning data augmented with pseudo-code representations of natural language instructions paired with final responses.
  • We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models.
  • Our results show that models trained with pseudo-code follow instructions more reliably, achieving relative gains of 8-21\% on instruction following benchmarks, while largely preserving and in some cases improving performance on…

Why It Matters For Eval

  • We evaluate our method on 12 publicly available benchmarks spanning instruction-following, mathematical reasoning, and commonsense reasoning, across six base models.
  • Our results show that models trained with pseudo-code follow instructions more reliably, achieving relative gains of 8-21\% on instruction following benchmarks, while largely preserving and in some cases improving performance on…

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Demonstrations

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Gap: Metric reporting is present

    No metric terms extracted.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote