Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

The ROI of Small Examples: Optimizing In-Context Learning Under Token Budgets

Anxo Perez, Jorge Gab\'in, Javier Parapar

Published

Nov 20, 2026

Citations

0

Trust level

Moderate

Usefulness score

55/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 20, 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.

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
55/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

Abstract

In-context learning (ICL) improves large language model performance at inference time without updating model parameters. However, these gains are not free: in practical deployments, longer prompts directly increase inference cost and latency. Under a fixed token budget, prompt construction therefore becomes a resource-allocation problem. While prior work has often focused on how many examples to include in ICL, we study the complementary question of whether the available budget is better spent on a few long demonstrations or on a larger number of shorter ones. We study this aspect in question answering (QA), by organizing candidate demonstrations into length-based bins and constructing prompts from examples within the same length range under fixed budgets. Experiments on two QA benchmarks (\textit{Beat the AI} and \textit{Natural Questions}), using six instruction-tuned LLMs, show that shorter demonstrations are generally the most effective use of prompt space. This effect is especially strong on \textit{Beat the AI}, and remains visible on NQ, although gains are smaller and saturate earlier in the long-context setting. An additional natural language inference experiment on ANLI R3 finds that one of the two shorter bins performs best for five of six models, although longer demonstrations remain competitive. Overall, our results highlight demonstration granularity as an important factor in prompt design.

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

strong

Demonstrations

Directly usable for protocol triage.

"While prior work has often focused on how many examples to include in ICL, we study the complementary question of whether the available budget is better spent on a few long demonstrations or on a larger number of shorter ones."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"In-context learning (ICL) improves large language model performance at inference time without updating model parameters."

Quality Controls

missing

Not reported

No explicit QC controls found.

"In-context learning (ICL) improves large language model performance at inference time without updating model parameters."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"In-context learning (ICL) improves large language model performance at inference time without updating model parameters."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"In-context learning (ICL) improves large language model performance at inference time without updating model parameters."

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
Demonstrations
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

In-context learning (ICL) improves large language model performance at inference time without updating model parameters.

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

Key takeaways

  • In-context learning (ICL) improves large language model performance at inference time without updating model parameters.
  • However, these gains are not free: in practical deployments, longer prompts directly increase inference cost and latency.
  • Under a fixed token budget, prompt construction therefore becomes a resource-allocation problem.

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.

Contribution summary

  • In-context learning (ICL) improves large language model performance at inference time without updating model parameters.
  • However, these gains are not free: in practical deployments, longer prompts directly increase inference cost and latency.

Why it matters for eval

  • Experiments on two QA benchmarks (\textit{Beat the AI} and \textit{Natural Questions}), using six instruction-tuned LLMs, show that shorter demonstrations are generally the most effective use of prompt space.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Demonstrations

  • 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

    No metric terms extracted.