Data of the "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" paper
AI & ML interests
LLM, trustworthy AI, AI security, privacy, calibration, hallucination
Recent Activity
View all activity
Papers
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution
Organization Card
This is the organization grouping all the models and datasets of the research papers written at Parameter Lab.
List of research articles of Parameter Lab
-
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Paper • 2601.15220 • Published • 9 -
Dr.LLM: Dynamic Layer Routing in LLMs
Paper • 2510.12773 • Published • 32 -
Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution
Paper • 2510.18019 • Published • 18 -
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
Paper • 2506.15674 • Published • 2
Data of the "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" paper
List of research articles of Parameter Lab
-
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Paper • 2601.15220 • Published • 9 -
Dr.LLM: Dynamic Layer Routing in LLMs
Paper • 2510.12773 • Published • 32 -
Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution
Paper • 2510.18019 • Published • 18 -
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
Paper • 2506.15674 • Published • 2
models 8
parameterlab/apricot_clustering_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification • 0.2B • Updated • 5
parameterlab/apricot_binary_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification • 0.2B • Updated • 5
parameterlab/apricot_clustering_trivia_qa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification • 0.2B • Updated • 5
parameterlab/apricot_binary_trivia_qa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification • 0.2B • Updated • 1
parameterlab/apricot_clustering_coqa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification • 0.2B • Updated • 5
parameterlab/apricot_binary_coqa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification • 0.2B • Updated • 5
parameterlab/apricot_binary_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification • 0.2B • Updated • 8 • 1
parameterlab/apricot_clustering_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification • 0.2B • Updated • 18
datasets 25
parameterlab/c-seo-results
Viewer • Updated • 143k • 117
parameterlab/c-seo-bench
Viewer • Updated • 16.4k • 140 • 3
parameterlab/leaky_thoughts
Updated • 48 • 2
parameterlab/scaling_mia_results
Updated • 76 • 1
parameterlab/scaling_mia_the_pile_00_Gutenberg_PG-19
Viewer • Updated • 2.34k • 19
parameterlab/scaling_mia_the_pile_00_PubMed_Central
Viewer • Updated • 202k • 19 • 1
parameterlab/scaling_mia_the_pile_00_Ubuntu_IRC
Viewer • Updated • 666 • 20
parameterlab/scaling_mia_the_pile_00_USPTO_Backgrounds
Viewer • Updated • 393k • 24
parameterlab/scaling_mia_the_pile_00_NIH_ExPorter
Viewer • Updated • 63.3k • 8
parameterlab/scaling_mia_the_pile_00_PubMed_Abstracts
Viewer • Updated • 1.04M • 9 • 2