SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.01254 · 2021

Principled Evaluation with Human Labels: One Rater at a Time and Rater Equivalence

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
presnick/surveyequivalence canonical 0 of 5
FunctionStatusWhere it lives
comb Not yet run presnick/surveyequivalence/surveyequivalence/scoring_functions.py
code served (permissive licence) · get_code("60473e3f787c8faf")
find_maximal_full_rating_matrix_cols Not yet run presnick/surveyequivalence/surveyequivalence/equivalence.py
code served (permissive licence) · get_code("f2a494e991c3343d")
frac Not yet run presnick/surveyequivalence/surveyequivalence/scoring_functions.py
code served (permissive licence) · get_code("b9b45546df332168")
mode Not yet run presnick/surveyequivalence/surveyequivalence/scoring_functions.py
code served (permissive licence) · get_code("ca691f11a2a20be0")
prep_anonymized_rating_matrix Not yet run presnick/surveyequivalence/surveyequivalence/equivalence.py
code served (permissive licence) · get_code("59d1b7594c98cb7b")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In many classification tasks, there is no definitive ground truth, only human judgments that may disagree. We address two challenges that arise in such settings: (1) how to use human raters to score classifiers, and (2) how to use them for comparison benchmarks. For the first, the common practice is to score classifiers against the majority vote of an evaluation panel of several human raters. We argue that this is not justified when either of two properties fails: objectivity or equanimity. Instead, under a utility model appropriate for such settings, scoring against one rater at a time and averaging the scores across raters is a more principled approach. For the second, we introduce the concept of rater equivalence: the smallest number of human raters whose combined judgment matches the classifier's performance. We provide a provably optimal algorithm for combining benchmark panel labels, and demonstrate the framework through case studies.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.01254")
get_code_for_paper("2106.01254")
have("2106.01254")

Connect an agent — have() is free.