Menu

Individual skill

emnlp-experiments

0upvotes

Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.

EMNLP-Skills/skills/emnlp-experiments/SKILL.md

Read pinned source

Source commit 932eb23331721b16e967c59f093781be1928b498

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,405
Repository last updated
Sep 27, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# EMNLP Experiments

Use this while the experimental grid is still cheap to change. EMNLP's reviewing culture
was partly built by papers criticizing NLP's own evaluation habits, so the venue audits
experiments the way a security reviewer audits inputs: assume the design will be probed
for the easiest way to make the headline number lie.

## The five probes reviewers run

1. **Baseline fairness.** Did the comparison systems get the same tuning budget, data,
   and prompt engineering effort as yours? A win over an under-tuned baseline is the
   most common EMNLP soundness objection.
2. **Coverage-claim match.** Do the datasets, domains, and languages span the claim?
   English-only evidence supports English-only sentences.
Back to top