5 citations · 9 across the 11 of their papers we have counts for
13 papers
How Persuasive is Your Context?
Tu Nguyen, Kevin Du, Alexander Miserlis Hoyle +1
Two central capabilities of language models (LMs) are: (i) drawing on prior knowledge about entities, which allows them to answer queries such as "What's the official language of A…
Taxonomy-Aware Evaluation of Vision-Language Models
Vésteinn Snæbjarnarson, Kevin Du, Niklas Stoehr +4
When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This rai…
Controllable Context Sensitivity and the Knob Behind It
Julian Minder, Kevin Du, Niklas Stoehr +4
When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamen…
Activation Scaling for Steering and Interpreting Language Models
Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson +3
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant act…
Context versus Prior Knowledge in Language Models
Kevin Du, Vésteinn Snæbjarnarson, Niklas Stoehr +3
To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perfor…
Principled Gradient-based Markov Chain Monte Carlo for Text Generation
Li Du, Afra Amini, Lucas Torroba Hennigen +4
Recent papers have demonstrated the possibility of energy-based text generation by adapting gradient-based sampling algorithms, a paradigm of MCMC algorithms that promises fast con…
Generalizing Backpropagation for Gradient-Based Interpretability
Kevin Du, Lucas Torroba Hennigen, Niklas Stoehr +2
Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs. While these methods c…
A Geometric Notion of Causal Probing
Clément Guerner, Tianyu Liu, Anej Svete +2
The linear subspace hypothesis (Bolukbasi et al., 2016) states that, in a language model's representation space, all information about a concept such as verbal number is encoded in…
The Ordered Matrix Dirichlet for State-Space Models
Niklas Stoehr, Benjamin J. Radford, Ryan Cotterell +1
Many dynamical systems in the real world are naturally described by latent states with intrinsic orderings, such as "ally", "neutral", and "enemy" relationships in international re…
An Ordinal Latent Variable Model of Conflict Intensity
Niklas Stoehr, Lucas Torroba Hennigen, Josef Valvoda +3
Measuring the intensity of events is crucial for monitoring and tracking armed conflict. Advances in automated event extraction have yielded massive data sets of "who did what to w…
A Latent-Variable Model for Intrinsic Probing
Karolina Stańczak, Lucas Torroba Hennigen, Adina Williams +2
The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that…
Probing as Quantifying Inductive Bias
Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin +1
Pre-trained contextual representations have led to dramatic performance improvements on a range of downstream tasks. Such performance improvements have motivated researchers to qua…
Classifying Dyads for Militarized Conflict Analysis
Niklas Stoehr, Lucas Torroba Hennigen, Samin Ahbab +2
Understanding the origins of militarized conflict is a complex, yet important undertaking. Existing research seeks to build this understanding by considering bi-lateral relationshi…