Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
UnBias-Plus: Detect, Explain, and Rewrite Bias
Ahmed Y. Radwan, Ahmed ElKady, Sindhuja Chaduvula +3
Bias in natural language remains a persistent challenge in both human-written and AI-generated content, affecting domains such as journalism, education, and AI research. Most exist…
cs.CL2026
Reducing Hallucinations in LLMs via Factuality-Aware Preference Learning
Sindhuja Chaduvula, Ahmed Y. Radwan, Azib Farooq +2
Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce hallucinations when preference judgmen…