作者位次 #2/7ACL 2026Poster· Natural Language Processing
CUB : Benchmarking Context Utilisation Techniques for Language Models
Lovisa Hagström · Youna Kim · Haeun Yu · Sang-goo Lee · Richard Johansson · Hyunsoo Cho · Isabelle Augenstein
摘要
Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that contradicts outdated parametric memory or be distracted by irrelevant contexts. While many context utilisati...