Papers with filtering techniques
ParaQG: A System for Generating Questions and Answers from Paragraphs (D19-3)
Copied to clipboard
| Challenge: | Automated question generation systems generate questions from sentences and paragraphs . manual generation of questions is labour-intensive as it requires reading, parsing and understanding of long passages of text. |
| Approach: | They propose a web-based system for generating questions from sentences and paragraphs . paraQG provides an interactive interface for a user to select answers with visual insights . |
| Outcome: | The proposed system generates questions from sentences and paragraphs on a web-based platform. |
Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent work has found that vision-language models trained under the Contrastive Language Image Pre-training framework contain intrinsic social biases, but how these biase relates to downstream performance has been unclear. |
| Approach: | They present the largest comprehensive analysis to-date of how upstream pre-training factors and downstream performance of CLIP models relate to their intrinsic biases. |
| Outcome: | The proposed model performance analysis shows that the choice of pre-training dataset is the most significant upstream predictor of bias, whereas architectural variations have minimal impact. |
Sing it, Narrate it: Quality Musical Lyrics Translation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing song translation approaches prioritize singability constraints at the expense of translation quality, which is crucial for musicals. |
| Approach: | They propose to automatically translate musical lyrics from English to Chinese to ensure high translation quality while adhering to singability requirements such as length and rhyme. |
| Outcome: | The proposed method improves both singability and translation quality over baseline methods and validates its effectiveness. |
Mastering the Craft of Data Synthesis for CodeLLMs (2025.naacl-long)
Copied to clipboard
Meng Chen, Philip Arthur, Qianyu Feng, Cong Duy Vu Hoang, Yu-Heng Hong, Mahdi Kazemi Moghaddam, Omid Nezami, Duc Thien Nguyen, Gioacchino Tangari, Duy Vu, Thanh Vu, Mark Johnson, Krishnaram Kenthapadi, Don Dharmasiri, Long Duong, Yuan-Fang Li
| Challenge: | Large language models (LLMs) have shown impressive performance in code understanding and generation. |
| Approach: | They propose a systematic review of large language models and their taxonomy and propose specialized LLMs for code-related tasks. |
| Outcome: | The proposed models have shown to be highly effective in coding tasks. |
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router (2026.acl-long)
Copied to clipboard
| Challenge: | Current alignment approaches rely on refusal alignment to avoid harmful content . large language models are often overly cautious or overlook subtle harmful content. |
| Approach: | They propose a framework for fine-grained safe generation in Large Language Models that enables real-time, token-level harmfulness detection and redaction without loss in capability. |
| Outcome: | The proposed framework achieves over 90% in F1 score for detecting and redacting harmful content while preserving overall utility and informativeness of the model’s responses. |