activity
20232025
collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling

Jannek Ulm, Kevin Du, Vésteinn Snæbjarnarson

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to…

cs.CL2025

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…

cs.CL20241 cited

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…

cs.CL2024

Efficiently Computing Susceptibility to Context in Language Models

Tianyu Liu, Kevin Du, Mrinmaya Sachan +1

One strength of modern language models is their ability to incorporate information from a user-input context when answering queries. However, they are not equally sensitive to the…

cs.CL2024

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…

cs.CL2024

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…