Papers by Mauricio Gruppi
ConShift: Sense-based Language Variation Analysis using Flexible Alignment (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for semantic variation analysis are limited due to the limited evaluation datasets available for word-level and sense-level variants. |
| Approach: | They propose a family of alignment-based algorithms that enable semantic variation analysis at the sense-level. |
| Outcome: | The proposed algorithms can detect multiple sense-level language variations while providing explanations through visualization of related concepts. |
On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning (2025.coling-main)
Copied to clipboard
| Challenge: | Text-based reinforcement learning is a form of interactive fiction where players manipulate the environment using text and admissible actions in natural language. |
| Approach: | They show that rich semantic understanding leads to efficient training of text-based RL agents . they also show that semantic degeneration occurs when LMs are inappropriately fine-tuned . |
| Outcome: | The results suggest that semantic understanding is not important for the task . they also show that fine-tuning language models can degenerate the agent's performance . |