13 papers · 1 filter
PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation
Saleh Afzoon, MohammadHossein Ahmadi, Usman Naseem +1
Personalization and contextual coherence are two essential components in building effective persona-grounded dialogue systems. These aspects play a crucial role in enhancing user e…
PersoBench: Benchmarking Personalized Response Generation in Large Language Models
Saleh Afzoon, Zahra Jamali, Usman Naseem +1
While large language models (LLMs) have exhibited impressive conversational capabilities, their proficiency in delivering personalized responses remains unclear. Although recent be…
Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette
Jiahao Yuan, Zixiang Di, Shangzixin Zhao +4
Large language models (LLMs) face challenges in aligning with diverse cultural values despite their remarkable performance in generation, which stems from inherent monocultural bia…
Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
Shangziqi Zhao, Jiahao Yuan, Jinyang Wu +3
Long chain-of-thought (Long-CoT) reasoning improves accuracy in LLMs, yet its verbose, self-reflective style often hinders effective distillation into small language models (SLMs).…
Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning
Jiahao Yuan, Zhiqing Cui, Hanqing Wang +3
As web platforms evolve towards greater personalization and emotional complexity, conversational agents must transcend superficial empathy to demonstrate identity-aware emotional r…
LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
Md Arid Hasan, Firoj Alam, Md Fahad Hossain +2
Online social media platforms are central to everyday communication and information seeking. While these platforms serve positive purposes, they also provide fertile ground for the…