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 • 7 -
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 • 7 -
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
•
9
parameterlab/apricot_binary_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
9
parameterlab/apricot_clustering_trivia_qa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
10
parameterlab/apricot_binary_trivia_qa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
2
parameterlab/apricot_clustering_coqa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
9
parameterlab/apricot_binary_coqa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
8
parameterlab/apricot_binary_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
5
•
1
parameterlab/apricot_clustering_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
12
datasets
25
parameterlab/c-seo-results
Viewer
•
Updated
•
143k
•
433
parameterlab/c-seo-bench
Viewer
•
Updated
•
16.4k
•
108
•
3
parameterlab/leaky_thoughts
Updated
•
44
•
2
parameterlab/scaling_mia_results
Updated
•
28
•
1
parameterlab/scaling_mia_the_pile_00_Gutenberg_PG-19
Viewer
•
Updated
•
2.34k
•
15
parameterlab/scaling_mia_the_pile_00_PubMed_Central
Viewer
•
Updated
•
202k
•
12
•
1
parameterlab/scaling_mia_the_pile_00_Ubuntu_IRC
Viewer
•
Updated
•
666
•
17
parameterlab/scaling_mia_the_pile_00_USPTO_Backgrounds
Viewer
•
Updated
•
393k
•
14
parameterlab/scaling_mia_the_pile_00_NIH_ExPorter
Viewer
•
Updated
•
63.3k
•
22
parameterlab/scaling_mia_the_pile_00_PubMed_Abstracts
Viewer
•
Updated
•
1.04M
•
25
•
2