Papers with ranking strategies
Interactive Word Completion for Plains Cree (2022.acl-long)
Copied to clipboard
| Challenge: | a tool that helps users incrementally build complex words is being developed in morphologically complex languages. |
| Approach: | They propose a finite state approach which maps prefixes in a language to completions up to the next morpheme boundary for incremental building of complex words. |
| Outcome: | The proposed approach shows portability to a larger, more complete morphological transducer. |
EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated dominant performance in text re-ranking. |
| Approach: | They propose a suite of budget-constrained methods to perform text re-ranking using LLMs. |
| Outcome: | The proposed method outperforms other budget-aware methods on four datasets. |
From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision–Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing models focus on single tasks, limiting comparability of neuron importance . ranking strategies overlook how task-dependent information pathways shape write-in effects of feed-forward network (FFN) neurons. |
| Approach: | They propose a gradient-free framework for task-aware neuron attribution and steering in multi-task vision-language models. |
| Outcome: | The proposed framework outperforms existing methods in identifying task-critical neurons and improves model performance after steering. |