33 citations · 98 across the 17 of their papers we have counts for
21 papers
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?
Sohee Yang, Sang-Woo Lee, Nora Kassner +3
Recent reasoning models show the ability to reflect, backtrack, and self-validate their reasoning, which is crucial in spotting mistakes and arriving at accurate solutions. A natur…
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
Sohee Yang, Nora Kassner, Elena Gribovskaya +2
We evaluate how well Large Language Models (LLMs) latently recall and compose facts to answer multi-hop queries like "In the year Scarlett Johansson was born, the Summer Olympics w…
BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models
Jacek Wiland, Max Ploner, Alan Akbik
Knowledge probing assesses to which degree a language model (LM) has successfully learned relational knowledge during pre-training. Probing is an inexpensive way to compare LMs of…
Do Large Language Models Latently Perform Multi-Hop Reasoning?
Sohee Yang, Elena Gribovskaya, Nora Kassner +2
We study whether Large Language Models (LLMs) latently perform multi-hop reasoning with complex prompts such as "The mother of the singer of 'Superstition' is". We look for evidenc…
Multilingual End to End Entity Linking
Mikhail Plekhanov, Nora Kassner, Kashyap Popat +5
Entity Linking is one of the most common Natural Language Processing tasks in practical applications, but so far efficient end-to-end solutions with multilingual coverage have been…
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Ayyoob Imani, Peiqin Lin, Amir Hossein Kargaran +8
The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we cr…