AIConfPaper
← Search

Jason Lucas

4 accepted papers

2026

Position: Breaking the Dual Curse of Multilingual AI Requires Socio-Technical Guardrails, Not Post-Hoc Alignment

Jason Lucas, Pureheart Ogheneogaga Irikefe, Adaku Uchendu, Umniya Najaer, Cornelius Adejoro, Patrice Sterling +1
ICML 2026poster

Large language models are deployed globally as universal systems, yet their safety mechanisms remain English-optimized. This creates a Dual Curse for speakers of low-resource languages: a Harmfulness Curse where harmful content generation rises from 1\% in English to 35\% in languages like Hausa, Ig…

Cited by 0Source ↗Scholar ↗
2025

Chain-of-Interactions: Multi-step Iterative ICL Framework for Abstractive Task-Oriented Dialogue Summarization of Conversational AI Interactions

Jason Lucas, John Chen, Ali Al-Lawati, Mahjabin Nahar, Mahnoosh Mehrabani
EMNLP 2025

Large Language Models (LLMs) have introduced paradigm-shifting approaches in natural language processing. Yet, their transformative in-context learning (ICL) capabilities remain underutilized, especially in customer service dialogue summarization—a domain plagued by generative hallucinations, detail

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text

Ali Al Lawati, Jason Lucas, Prasenjit Mitra
COLING 2025main

Large Language Models (LLMs) have demonstrated remarkable performance in various NLP tasks, including semantic parsing, which translates natural language into formal code representations. However, the reverse operation, translating code into natural language, termed semantic captioning, has received…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗