16 citations · 31 across the 14 of their papers we have counts for
14 papers
Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops
Faeze Ghorbanpour, Constanza Fierro, Alexander Fraser +1
Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space intervention can reduce this inconsist…
Pathways of Visual Information Flow in Vision-Language Models
Israfel Salazar, Stella Frank, Dan Oneata +2
We study how visual information is routed in vision-language models (VLMs). Using causal patching on controlled synthetic and natural datasets, we find that models rely on two dist…
Steering Language Models with Weight Arithmetic
Constanza Fierro, Fabien Roger
Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribut…
Real-Time Progress Prediction in Reasoning Language Models
Hans Peter Lyngsøe Raaschou-Jensen, Constanza Fierro, Anders Søgaard
Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operat…
Mechanistic Interpretability Needs Philosophy
Iwan Williams, Ninell Oldenburg, Ruchira Dhar +6
Mechanistic interpretability (MI) aims to explain how neural networks work by uncovering their underlying mechanisms. As the field grows in influence, it is increasingly important…
Defining Knowledge: Bridging Epistemology and Large Language Models
Constanza Fierro, Ruchira Dhar, Filippos Stamatiou +2
Knowledge claims are abundant in the literature on large language models (LLMs); but can we say that GPT-4 truly "knows" the Earth is round? To address this question, we review sta…
How Do Multilingual Language Models Remember Facts?
Constanza Fierro, Negar Foroutan, Desmond Elliott +1
Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowle…
MuLan: A Study of Fact Mutability in Language Models
Constanza Fierro, Nicolas Garneau, Emanuele Bugliarello +2
Facts are subject to contingencies and can be true or false in different circumstances. One such contingency is time, wherein some facts mutate over a given period, e.g., the presi…
Does Instruction Tuning Make LLMs More Consistent?
Constanza Fierro, Jiaang Li, Anders Søgaard
The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al.…
Learning to Plan and Generate Text with Citations
Constanza Fierro, Reinald Kim Amplayo, Fantine Huot +4
The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with…
PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge
Fantine Huot, Joshua Maynez, Chris Alberti +5
Cross-lingual summarization consists of generating a summary in one language given an input document in a different language, allowing for the dissemination of relevant content acr…
Factual Consistency of Multilingual Pretrained Language Models
Constanza Fierro, Anders Søgaard
Pretrained language models can be queried for factual knowledge, with potential applications in knowledge base acquisition and tasks that require inference. However, for that, we n…
Challenges and Strategies in Cross-Cultural NLP
Daniel Hershcovich, Stella Frank, Heather Lent +11
Various efforts in the Natural Language Processing (NLP) community have been made to accommodate linguistic diversity and serve speakers of many different languages. However, it is…
Predicting Unplanned Readmissions with Highly Unstructured Data
Constanza Fierro, Jorge Pérez, Javier Mora
Deep learning techniques have been successfully applied to predict unplanned readmissions of patients in medical centers. The training data for these models is usually based on his…