38 citations · 65 across the 11 of their papers we have counts for
13 papers
MLCommons Jailbreak Benchmark v1.0
Carsten Maple, Cagatay Yucel, Isaac Holeman +33
Modern AI systems are designed to refuse hazardous requests. A jailbreak is a prompt crafted to bypass those safeguards and elicit outputs that the system would normally refuse to…
Is this Citation on Point?
Apurv Verma
In 2023, a New York judge sanctioned two attorneys in Mata v. Avianca for filing a brief with hallucinated citations generated by ChatGPT. Such failures are largely caught by datab…
From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10
The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021, has grown from 8 proceedings papers to 41 over six editions, d…
LLM-as-a-Judge: Rapid Evaluation of Legal Document Recommendation for Retrieval-Augmented Generation
Anu Pradhan, Alexandra Ortan, Apurv Verma +1
The evaluation bottleneck in recommendation systems has become particularly acute with the rise of Generative AI, where traditional metrics fall short of capturing nuanced quality…
Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
Haoran Zhou, Xingchen Song, Brendan Fahy +9
OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence…
Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
Apurv Verma, NhatHai Phan, Shubhendu Trivedi
Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training…
Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)
Apurv Verma, Satyapriya Krishna, Sebastian Gehrmann +7
Creating secure and resilient applications with large language models (LLM) requires anticipating, adjusting to, and countering unforeseen threats. Red-teaming has emerged as a cri…
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Ninareh Mehrabi, Palash Goyal, Apurv Verma +7
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions…
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model
Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald +13
In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, ar…
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Umang Gupta, Jwala Dhamala, Varun Kumar +7
Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However,…
Measuring Fairness of Text Classifiers via Prediction Sensitivity
Satyapriya Krishna, Rahul Gupta, Apurv Verma +3
With the rapid growth in language processing applications, fairness has emerged as an important consideration in data-driven solutions. Although various fairness definitions have b…
A Stochastic Differential Equation Framework for Guiding Online User Activities in Closed Loop
Yichen Wang, Evangelos Theodorou, Apurv Verma +1
Recently, there is a surge of interest in using point processes to model continuous-time user activities. This framework has resulted in novel models and improved performance in di…
Detecting weak changes in dynamic events over networks
Shuang Li, Yao Xie, Mehrdad Farajtabar +2
Large volume of networked streaming event data are becoming increasingly available in a wide variety of applications, such as social network analysis, Internet traffic monitoring a…