Papers with objective criteria
Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts (D19-1)
Copied to clipboard
| Challenge: | Existing tools for hate speech detection and sentiment analysis cannot detect veiled offensiveness of microaggressions . linguistic subtlety of micro-aggressives has made it difficult to analyze their exact nature . |
| Approach: | They propose a typology of microaggressions based on a subset of data . they propose an objective criterion for annotation and an active-learning procedure . |
| Outcome: | The proposed typology of microaggressions is based on a subset of social media data. |
M-IFEval: Multilingual Instruction-Following Evaluation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Instruction following is a core capability of Large language models (LLMs), making evaluating this capability essential to understanding these models. |
| Approach: | They propose a multilingual instruction following evaluation benchmark that expands to other languages . they propose to use both general and language-specific instructions to evaluate LLMs . |
| Outcome: | The proposed benchmark is extended to French, Japanese, and Spanish . it shows that performance across languages and instruction types can vary widely . |
Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation (2025.findings-acl)
Copied to clipboard
Hongzhe Huang, Jiang Liu, Zhewen Yu, Li Cai, Dian Jiao, Wenqiao Zhang, Siliang Tang, Juncheng Li, Hao Jiang, Haoyuan Li, Yueting Zhuang
| Challenge: | Recent advances in Multi-modal Large Language Models (MLLMs) introduce significant variability in data quality. |
| Approach: | They propose to use human and LLM preference alignment to compress large corpus of machine-generated multimodal instructions into a compact and high-quality form. |
| Outcome: | The proposed algorithm outperforms LLaVA-series models in MLLM benchmarks by 90% . it uses human and LLM preference alignment to compress a large dataset . |