7 papers
Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
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…
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Elicitation
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 behaviour is…
CulTrace: Tracing Internal Cultural Reasoning in Large Language Models
Haeun Yu, Arnav Arora Seogyeong Jeong, Seogyeong Jeong +8
The growing deployment of large language models (LLMs) across diverse cultural contexts necessitates a deeper understanding of models' hidden representations of different cultures.…
Unstructured Evidence Attribution for Long Context Query Focused Summarization
Dustin Wright, Zain Muhammad Mujahid, Lu Wang +2
Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query, and extracting and citing evidence spans helps improve the tru…
Multi-Modal Framing Analysis of News
Arnav Arora, Srishti Yadav, Maria Antoniak +2
Automated frame analysis of political communication is a popular task in computational social science that is used to study how authors select aspects of a topic to frame its recep…
Presumed Cultural Identity: How Names Shape LLM Responses
Siddhesh Pawar, Arnav Arora, Lucie-Aimée Kaffee +1
Names are deeply tied to human identity. They can serve as markers of individuality, cultural heritage, and personal history. However, using names as a core indicator of identity c…