◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Kevin Leach

7 papers hereh-index 315 citations10 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • last author7

Across the 7 of 7 papers where every author was matched, so the position is known.

fields
  • cs.CL4
  • cs.CV1
  • cs.HC1
  • cs.LG1
same name
  • Kevin Leach — 10 papers, h 5
  • Kevin Leach — 10 papers, h 3
  • Kevin Leach — 8 papers, h 19
  • Kevin Leach — 4 papers, h 1
  • Kevin Leach — 3 papers

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

most citedGenerating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

4 papers · 1 filter

cs.CL2026

Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss

Zhijian Li, Stefan Larson, Kevin Leach

Large language models are typically trained under uniform token weighting, which allows frequent and low-information tokens to dominate learning and can increase the tendency to me…

cs.CL2026

Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap

Stefan Larson, Attila Nagy, Sam Desai +8

RVL-CDIP is a popular dataset for benchmarking document classifiers. However, the dataset contains ample amounts of label errors as well as non-trivial amounts of test-train overla…

cs.CL2024

Document Classification using File Names

Zhijian Li, Stefan Larson, Kevin Leach

Rapid document classification is critical in several time-sensitive applications like digital forensics and large-scale media classification. Traditional approaches that rely on he…

cs.CL2024★ 1 cited

Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification

Zhijian Li, Stefan Larson, Kevin Leach

Intent classifiers must be able to distinguish when a user's utterance does not belong to any supported intent to avoid producing incorrect and unrelated system responses. Although…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.