10 papers · 1 filter
A Grounded Typology of Word Classes
Coleman Haley, Sharon Goldwater, Edoardo Ponti
We propose a grounded approach to meaning in language typology. We treat data from perceptual modalities, such as images, as a language-agnostic representation of meaning. Hence, w…
Mixtures of In-Context Learners
Giwon Hong, Emile van Krieken, Edoardo Ponti +2
In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratica…
Spectral Editing of Activations for Large Language Model Alignment
Yifu Qiu, Zheng Zhao, Yftah Ziser +3
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effe…
Cross-Lingual and Cross-Cultural Variation in Image Descriptions
Uri Berger, Edoardo M. Ponti
Do speakers of different languages talk differently about what they see? Behavioural and cognitive studies report cultural effects on perception; however, these are mostly limited…
Model Merging by Uncertainty-Based Gradient Matching
Nico Daheim, Thomas Möllenhoff, Edoardo Maria Ponti +2
Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weight…
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
Piotr Nawrot, Adrian ÅaÅcucki, Marcin Chochowski +2
Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value represent…