1 citations · 2 across the 11 of their papers we have counts for
11 papers
Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
Ming Shen, Chao Shang, Sadat Shahriar +4
Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create implicit expectations of trust, s…
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting
Devang Kulshreshtha, Hang Su, Haibo Jin +2
We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts o…
The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems
Devang Kulshreshtha, Wanyu Du, Raghav Jain +4
This paper introduces a novel framework for simulating and analyzing how uncooperative behaviors can destabilize or collapse LLM-based multi-agent systems. Our framework includes t…
STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
Jing-Jing Li, Jianfeng He, Chao Shang +6
As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper i…
Sequential Editing for Lifelong Training of Speech Recognition Models
Devang Kulshreshtha, Saket Dingliwal, Brady Houston +2
Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining mo…
Retrieve and Copy: Scaling ASR Personalization to Large Catalogs
Sai Muralidhar Jayanthi, Devang Kulshreshtha, Saket Dingliwal +2
Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing…
Generalized zero-shot audio-to-intent classification
Veera Raghavendra Elluru, Devang Kulshreshtha, Rohit Paturi +2
Spoken language understanding systems using audio-only data are gaining popularity, yet their ability to handle unseen intents remains limited. In this study, we propose a generali…
Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languages
Devang Kulshreshtha, Saket Dingliwal, Brady Houston +1
Connectionist Temporal Classification (CTC) models are popular for their balance between speed and performance for Automatic Speech Recognition (ASR). However, these CTC models sti…
Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation
Nilaksh Das, Monica Sunkara, Sravan Bodapati +4
End-to-end ASR models trained on large amount of data tend to be implicitly biased towards language semantics of the training data. Internal language model estimation (ILME) has be…
Few-shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems
Devang Kulshreshtha, Muhammad Shayan, Robert Belfer +3
Existing work on generating hints in Intelligent Tutoring Systems (ITS) focuses mostly on manual and non-personalized feedback. In this work, we explore automatically generated que…
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban +1
In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA) from source to target domain. While self-training generates synth…