3 citations · 3 across the 4 of their papers we have counts for
6 papers
Patches of Nonlinearity: Instruction Vectors in Large Language Models
Irina Bigoulaeva, Jonas Rohweder, Subhabrata Dutta +1
Despite the recent success of instruction-tuned language models and their ubiquitous usage, very little is known of how models process instructions internally. In this work, we add…
Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling
Federico Tiblias, Irina Bigoulaeva, Jingcheng Niu +2
The linear representation hypothesis states that language models (LMs) encode concepts as directions in their latent space, forming organized, multidimensional manifolds. Prior wor…
The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities
Irina Bigoulaeva, Harish Tayyar Madabushi, Iryna Gurevych
Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, e…
Are Emergent Abilities in Large Language Models just In-Context Learning?
Sheng Lu, Irina Bigoulaeva, Rachneet Sachdeva +2
Large language models, comprising billions of parameters and pre-trained on extensive web-scale corpora, have been claimed to acquire certain capabilities without having been speci…
Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5
Irina Bigoulaeva, Rachneet Sachdeva, Harish Tayyar Madabushi +2
We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the othe…
Addressing the Challenges of Cross-Lingual Hate Speech Detection
Irina Bigoulaeva, Viktor Hangya, Iryna Gurevych +1
The goal of hate speech detection is to filter negative online content aiming at certain groups of people. Due to the easy accessibility of social media platforms it is crucial to…