3 papers
cs.CL2024
Mitigating Bias for Question Answering Models by Tracking Bias Influence
Mingyu Derek Ma, Jiun-Yu Kao, Arpit Gupta +6
Models of various NLP tasks have been shown to exhibit stereotypes, and the bias in the question answering (QA) models is especially harmful as the output answers might be directly…
cs.CL2024
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal +2
Decoding methods for large language models (LLMs) usually struggle with the tradeoff between ensuring factuality and maintaining diversity. For example, a higher p threshold in the…
cs.CL2024
DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
Sidi Lu, Wenbo Zhao, Chenyang Tao +4
NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving gua…