5 papers
Power law attention biases for molecular transformers
Jay Shen, Yifeng Tang, Andrew Ferguson
Transformers are the go-to architecture for most data modalities due to their scalability. While they have been applied extensively to molecular property prediction, they do not do…
A Benchmark for Localizing Code and Non-Code Issues in Software Projects
Zejun Zhang, Jian Wang, Qingyun Yang +7
Accurate project localization (e.g., files and functions) for issue resolution is a critical first step in software maintenance. However, existing benchmarks for issue localization…
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
Zhenjie Xu, Wenqing Chen, Yi Tang +6
Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially bia…
Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
Jialiang Wu, Yi Shen, Sijia Liu +4
Despite their impressive capacities, Large language models (LLMs) often struggle with the hallucination issue of generating inaccurate or fabricated content even when they possess…
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
Huandong Wang, Wenjie Fu, Yingzhou Tang +7
While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant…