Papers by Alessandro Roncone
ReSeeding Latent States for Sequential Language Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing grounding approaches depend on auxiliary modules at inference or implicitly align encoder-only models that lack generative capacity. |
| Approach: | They propose a method that produces latent embeddings aligned with the true state of the environment and refeeds these embeddables into the model before generating its output. |
| Outcome: | The proposed method outperforms commercial LLMs on three new reasoning benchmarks. |
The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has raised concerns about the inherent limitations of text-only pretraining. |
| Approach: | They first generate a color dataset of human-perceived color distributions for 521 common objects and then use it to analyze and compare the color distribution found in text and the distribution captured by language models. |
| Outcome: | The proposed model improves on the CoDa color distribution, while the language model improve on the ground-truth distribution. |
PROST: Physical Reasoning about Objects through Space and Time (2021.findings-acl)
Copied to clipboard
| Challenge: | a new dataset is available to test pretraining of physical reasoning models . state-of-the-art models are inadequate at reasoning about physical interactions, authors say . |
| Approach: | They present a dataset that contains 18,736 multiple-choice questions from 14 templates . they propose to use the dataset to probe both causal and masked language models . |
| Outcome: | The proposed dataset contains 18,736 multiple-choice questions covering 10 physical reasoning concepts. |