Alert button
Picture for Tharindu Kumarage

Tharindu Kumarage

Alert button

Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey

Nov 14, 2023
Garima Agrawal, Tharindu Kumarage, Zeyad Alghami, Huan Liu

Viaarxiv icon

How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts

Oct 08, 2023
Tharindu Kumarage, Paras Sheth, Raha Moraffah, Joshua Garland, Huan Liu

Figure 1 for How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
Figure 2 for How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
Figure 3 for How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
Figure 4 for How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
Viaarxiv icon

ConDA: Contrastive Domain Adaptation for AI-generated Text Detection

Sep 20, 2023
Amrita Bhattacharjee, Tharindu Kumarage, Raha Moraffah, Huan Liu

Figure 1 for ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
Figure 2 for ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
Figure 3 for ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
Figure 4 for ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
Viaarxiv icon

J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News

Sep 06, 2023
Tharindu Kumarage, Amrita Bhattacharjee, Djordje Padejski, Kristy Roschke, Dan Gillmor, Scott Ruston, Huan Liu, Joshua Garland

Figure 1 for J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News
Figure 2 for J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News
Figure 3 for J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News
Figure 4 for J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News
Viaarxiv icon

Neural Authorship Attribution: Stylometric Analysis on Large Language Models

Aug 14, 2023
Tharindu Kumarage, Huan Liu

Figure 1 for Neural Authorship Attribution: Stylometric Analysis on Large Language Models
Figure 2 for Neural Authorship Attribution: Stylometric Analysis on Large Language Models
Figure 3 for Neural Authorship Attribution: Stylometric Analysis on Large Language Models
Viaarxiv icon

Causality Guided Disentanglement for Cross-Platform Hate Speech Detection

Aug 10, 2023
Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu

Figure 1 for Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
Figure 2 for Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
Figure 3 for Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
Figure 4 for Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
Viaarxiv icon

PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework

Jun 15, 2023
Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu

Figure 1 for PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework
Figure 2 for PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework
Figure 3 for PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework
Figure 4 for PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework
Viaarxiv icon

Stylometric Detection of AI-Generated Text in Twitter Timelines

Mar 07, 2023
Tharindu Kumarage, Joshua Garland, Amrita Bhattacharjee, Kirill Trapeznikov, Scott Ruston, Huan Liu

Figure 1 for Stylometric Detection of AI-Generated Text in Twitter Timelines
Figure 2 for Stylometric Detection of AI-Generated Text in Twitter Timelines
Figure 3 for Stylometric Detection of AI-Generated Text in Twitter Timelines
Figure 4 for Stylometric Detection of AI-Generated Text in Twitter Timelines
Viaarxiv icon