243 citations · 564 across the 13 of their papers we have counts for
15 papers
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
Watermarking Needs Input Repetition Masking
David Khachaturov, Robert Mullins, Ilia Shumailov +1
Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine l…
Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation
Ryutaro Tanno, David G. T. Barrett, Andrew Sellergren +23
Radiology reports are an instrumental part of modern medicine, informing key clinical decisions such as diagnosis and treatment. The worldwide shortage of radiologists, however, re…
Improving alignment of dialogue agents via targeted human judgements
Amelia Glaese, Nat McAleese, Maja Trębacz +31
We present Sparrow, an information-seeking dialogue agent trained to be more helpful, correct, and harmless compared to prompted language model baselines. We use reinforcement lear…
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
Maribeth Rauh, John Mellor, Jonathan Uesato +9
Large language models produce human-like text that drive a growing number of applications. However, recent literature and, increasingly, real world observations, have demonstrated…
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Jack W. Rae, Sebastian Borgeaud, Trevor Cai +77
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world.…
Challenges in Detoxifying Language Models
Johannes Welbl, Amelia Glaese, Jonathan Uesato +7
Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of saf…
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dvijotham +5
Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabil…
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin +8
Convex relaxations have emerged as a promising approach for verifying desirable properties of neural networks like robustness to adversarial perturbations. Widely used Linear Progr…
Plug-and-Play Conversational Models
Andrea Madotto, Etsuko Ishii, Zhaojiang Lin +2
There has been considerable progress made towards conversational models that generate coherent and fluent responses; however, this often involves training large language models on…
Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification
Daniel J. Mankowitz, Dan A. Calian, Rae Jeong +5
Many real-world physical control systems are required to satisfy constraints upon deployment. Furthermore, real-world systems are often subject to effects such as non-stationarity,…
Counter-example Guided Learning of Bounds on Environment Behavior
Yuxiao Chen, Sumanth Dathathri, Tung Phan-Minh +1
There is a growing interest in building autonomous systems that interact with complex environments. The difficulty associated with obtaining an accurate model for such environments…
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
Sumanth Dathathri, Andrea Madotto, Janice Lan +5
Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated languag…
Detecting Adversarial Examples via Neural Fingerprinting
Sumanth Dathathri, Stephan Zheng, Tianwei Yin +2
Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effect…
Decomposing GR(1) Games with Singleton Liveness Guarantees for Efficient Synthesis
Sumanth Dathathri, Richard M. Murray
Temporal logic based synthesis approaches are often used to find trajectories that are correct-by-construction for tasks in systems with complex behavior. Some examples of such tas…