5 citations · 12 across the 10 of their papers we have counts for
10 papers
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
Denitsa Saynova, Lovisa Hagström, Moa Johansson +2
Language models (LMs) can make a correct prediction based on many possible signals in a prompt, not all corresponding to recall of factual associations. However, current interpreta…
NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions
Elliot Gestrin, Marco Kuhlmann, Jendrik Seipp
Classical planners are powerful systems, but modeling tasks in input formats such as PDDL is tedious and error-prone. In contrast, planning with Large Language Models (LLMs) allows…
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
Emanuel Sanchez Aimar, Nathaniel Helgesen, Yonghao Xu +2
Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. Thi…
Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models
Ehsan Doostmohammadi, Tobias Norlund, Marco Kuhlmann +1
Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented mode…
On the Generalization Ability of Retrieval-Enhanced Transformers
Tobias Norlund, Ehsan Doostmohammadi, Richard Johansson +1
Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown that off-loading memory from trainable weights to a retrieval database can significantly improve language…
Balanced Product of Calibrated Experts for Long-Tailed Recognition
Emanuel Sanchez Aimar, Arvi Jonnarth, Michael Felsberg +1
Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited genera…