4 citations · 5 across the 7 of their papers we have counts for
8 papers
Consensus as Privileged Context for Label-Free Self-Distillation
John Gkountouras, Josip Jukić, Ivan Titov
Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growi…
Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
John Gkountouras, Ivan Titov
Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text…
Controlling What You Share: Assessing Language Model Adherence to Privacy Preferences
Guillem Ramírez, Alexandra Birch, Ivan Titov
Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how user…
Language Agents Meet Causality -- Bridging LLMs and Causal World Models
John Gkountouras, Matthias Lindemann, Phillip Lippe +2
Large Language Models (LLMs) have recently shown great promise in planning and reasoning applications. These tasks demand robust systems, which arguably require a causal understand…
Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations
Matthias Lindemann, Alexander Koller, Ivan Titov
Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are…
Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection
Guillem Ramírez, Alexandra Birch, Ivan Titov
Researchers and practitioners operating on a limited budget face the cost-performance trade-off dilemma. The challenging decision often centers on whether to use a large LLM with b…
Cache & Distil: Optimising API Calls to Large Language Models
Guillem Ramírez, Matthias Lindemann, Alexandra Birch +1
Large-scale deployment of generative AI tools often depends on costly API calls to a Large Language Model (LLM) to fulfil user queries. To curtail the frequency of these calls, one…
SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation
Matthias Lindemann, Alexander Koller, Ivan Titov
Strong inductive biases enable learning from little data and help generalization outside of the training distribution. Popular neural architectures such as Transformers lack strong…