Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations

no code implementations • 9 Mar 2024 • Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy, Inkit Padhi, David Piorkowski, Ambrish Rawat, Orna Raz, Prasanna Sattigeri, Hendrik Strobelt, Sarathkrishna Swaminathan, Christoph Tillmann, Aashka Trivedi, Kush R. Varshney, Dennis Wei, Shalisha Witherspooon, Marcel Zalmanovici

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.

Efficient Models for the Detection of Hate, Abuse and Profanity

no code implementations • 8 Feb 2024 • Christoph Tillmann, Aashka Trivedi, Bishwaranjan Bhattacharjee

This is unacceptable in civil discourse. The detection of Hate, Abuse and Profanity in text is a vital component of creating civil and unbiased LLMs, which is needed not only for English, but for all languages.

Document Classification named-entity-recognition +3

Muted: Multilingual Targeted Offensive Speech Identification and Visualization

no code implementations • 18 Dec 2023 • Christoph Tillmann, Aashka Trivedi, Sara Rosenthal, Santosh Borse, Rong Zhang, Avirup Sil, Bishwaranjan Bhattacharjee

Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web.

Sentence

Improved Sentence-Level Arabic Dialect Classification

no code implementations • WS 2014 • Christoph Tillmann, Saab Mansour, Yaser Al-Onaizan

Classification Feature Engineering +4