Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models ACL

Abhishek Kumar | Sarfaroz Yunusov | Ali Emami |

Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization F i n d i n g s - A C L

Cheng-Yu Hsieh | Yung-Sung Chuang | Chun-Liang Li | Zifeng Wang | Long Le | Abhishek Kumar | James Glass | Alexander Ratner | Chen-Yu Lee | Ranjay Krishna | Tomas Pfister |

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models ACL

Abhishek Kumar | Robert Morabito | Sanzhar Umbet | Jad Kabbara | Ali Emami |