◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Pratiksha Thaker

14 papers hereh-index 11784 citations32 works total

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

author position
  • first author4
  • middle author9
  • last author1

Across the 14 of 14 papers where every author was matched, so the position is known.

fields
  • cs.LG6
  • cs.AI2
  • cs.CL2
  • cs.CR2
  • cs.CY1
  • stat.ML1

identity via Semantic Scholar / OpenAlex

activity
20202026
most citedOverlook: Differentially Private Exploratory Visualization for Big Data

9 citations · 10 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2024★ 1 cited

Position: LLM Unlearning Benchmarks are Weak Measures of Progress

Pratiksha Thaker, Shengyuan Hu, Neil Kale +3

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning re…

cs.CL2024★ 4 cited

Guardrail Baselines for Unlearning in LLMs

Pratiksha Thaker, Yash Maurya, Shengyuan Hu +2

Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both gen…

◍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.