Papers with objective evaluation metrics
WildSci: Advancing Scientific Reasoning from In-the-Wild Literature (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language model reasoning focus on mathematics and coding domains, but scientific reasoning remains limited in other domains due to limited dataset coverage. |
| Approach: | They propose a framework for sustainable scientific reasoning QA generation by synthesizing a new dataset of domain-specific science questions from peer-reviewed literature. |
| Outcome: | The proposed framework and dataset enable scalable and sustainable research in scientific reasoning. |
CIS-BWE: Chaos-Informed Speech Bandwidth Extension (2026.acl-long)
Copied to clipboard
| Challenge: | CIS-BWE introduces two chaos-informed discriminators for capturing the deterministic chaos from speech. |
| Approach: | They propose a novel adversarial Bandwidth Extension framework that introduces two chaos-informed discriminators for capturing the deterministic chaos from speech. |
| Outcome: | The proposed framework achieves better performance across nine subjective and objective evaluation metrics with a 40x reduction in discriminator size and overall 0.5x fewer parameters, establishing a new baseline in the BWE task. |