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
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
-
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
Paper • 2411.00154 • Published -
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
Paper • 2402.12991 • Published -
Calibrating Large Language Models Using Their Generations Only
Paper • 2403.05973 • Published -
ProPILE: Probing Privacy Leakage in Large Language Models
Paper • 2307.01881 • Published • 1
Data of the "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" paper
List of research articles of Parameter Lab
-
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
Paper • 2411.00154 • Published -
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
Paper • 2402.12991 • Published -
Calibrating Large Language Models Using Their Generations Only
Paper • 2403.05973 • Published -
ProPILE: Probing Privacy Leakage in Large Language Models
Paper • 2307.01881 • Published • 1
models
8
parameterlab/apricot_clustering_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
22
parameterlab/apricot_binary_coqa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
23
parameterlab/apricot_clustering_trivia_qa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
18
parameterlab/apricot_binary_trivia_qa_deberta-v3-base_for_gpt-3.5-turbo-0125
Text Classification
•
0.2B
•
Updated
•
18
parameterlab/apricot_clustering_coqa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
36
parameterlab/apricot_binary_coqa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
26
parameterlab/apricot_binary_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
67
•
1
parameterlab/apricot_clustering_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
Text Classification
•
0.2B
•
Updated
•
17
datasets
25
parameterlab/leaky_thoughts
Updated
•
31
•
1
parameterlab/c-seo-results
Updated
•
204
parameterlab/c-seo-bench
Viewer
•
Updated
•
16.4k
•
203
•
2
parameterlab/scaling_mia_results
Updated
•
60
•
1
parameterlab/scaling_mia_the_pile_00_Gutenberg_PG-19
Viewer
•
Updated
•
2.34k
•
50
parameterlab/scaling_mia_the_pile_00_PubMed_Central
Viewer
•
Updated
•
202k
•
151
•
1
parameterlab/scaling_mia_the_pile_00_Ubuntu_IRC
Viewer
•
Updated
•
666
•
30
parameterlab/scaling_mia_the_pile_00_USPTO_Backgrounds
Viewer
•
Updated
•
393k
•
75
parameterlab/scaling_mia_the_pile_00_NIH_ExPorter
Viewer
•
Updated
•
63.3k
•
53
parameterlab/scaling_mia_the_pile_00_PubMed_Abstracts
Viewer
•
Updated
•
1.04M
•
75
•
2