activity
20232025
most citedGPT-Sentinel: Distinguishing Human and ChatGPT Generated Content

18 citations · 23 across the 15 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2025

No Encore: Unlearning as Opt-Out in Music Generation

Jinju Kim, Taehan Kim, Abdul Waheed +2

AI music generation is rapidly emerging in the creative industries, enabling intuitive music generation from textual descriptions. However, these systems pose risks in exploitation…

cs.CL2024

Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?

Roshan Sharma, Suwon Shon, Mark Lindsey +3

Reference summaries for abstractive speech summarization require human annotation, which can be performed by listening to an audio recording or by reading textual transcripts of th…

cs.CL20234 cited

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model

Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal +10

It has been shown that Large Language Model (LLM) alignments can be circumvented by appending specially crafted attack suffixes with harmful queries to elicit harmful responses. To…

cs.CL2023

Evaluating Speech Synthesis by Training Recognizers on Synthetic Speech

Dareen Alharthi, Roshan Sharma, Hira Dhamyal +3

Modern speech synthesis systems have improved significantly, with synthetic speech being indistinguishable from real speech. However, efficient and holistic evaluation of synthetic…

cs.CL2023

BASS: Block-wise Adaptation for Speech Summarization

Roshan Sharma, Kenneth Zheng, Siddhant Arora +3

End-to-end speech summarization has been shown to improve performance over cascade baselines. However, such models are difficult to train on very large inputs (dozens of minutes or…

cs.CL202318 cited

GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content

Yutian Chen, Hao Kang, Vivian Zhai +3

This paper presents a novel approach for detecting ChatGPT-generated vs. human-written text using language models. To this end, we first collected and released a pre-processed data…