5 papers
Emergence of Context Characteristics Sensitivity in Large Language Models
Nadya Yuki Wangsajaya, Haeun Yu, Isabelle Augenstein
During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While prior work has studied how co…
CulTrace: Tracing Internal Cultural Reasoning in Large Language Models
Haeun Yu, Arnav Arora, Seogyeong Jeong +7
The growing deployment of large language models (LLMs) across diverse cultural contexts necessitates a deeper understanding of models' hidden representations of different cultures.…
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection
Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar +3
Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation strategies. However, biased behavior is o…
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
Sara Vera Marjanović, Haeun Yu, Pepa Atanasova +3
Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated k…
Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods
Haeun Yu, Pepa Atanasova, Isabelle Augenstein
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant cha…