Peer-reviewed work in NLP, LLM safety, dialogue systems, and the use of LLMs in the legal domain.

CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment

ACL 2026 · main conference

Radin Shayanfar, Chu Fei Luo, Rohan V. Bhambhoria, Samuel Dahan, Xiaodan Zhu.

Introduces an interpretable framework that aligns LLM behaviour with explicit dialogue flows derived from expert knowledge. Achieved new state-of-the-art results on STAR and competitive results on MultiWOZ.

dialogue-systemsinterpretabilityLLMs

RedDebate: Safer Responses through Multi-Agent Red Teaming Debates

ICML 2026

Ali Asad, Stephen Obadinma, Radin Shayanfar, Xiaodan Zhu.

A multi-agent debating framework that strengthens LLM safety by having adversarial agents probe outputs through structured red-teaming debate.

LLM-safetymulti-agentred-teaming

Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation

Findings of EMNLP 2024 · pp. 15749–15768, Miami, FL

Chu Fei Luo, Radin Shayanfar, Rohan V. Bhambhoria, Samuel Dahan, Xiaodan Zhu.

Introduces a new task for using legally-grounded LLMs to detect misinformation with legal consequences. Compares two RAG-based approaches.

NLPlegalRAG

Full citation record on Google Scholar.