Papers with ERM
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for minimizing the worst-case loss of annotated groups are lacking in practice due to expensive annotations and privacy issues. |
| Approach: | They propose a distributionally robust optimization framework that relaxes group identification into direct parameterization by using an interactive training mode. |
| Outcome: | The proposed method outperforms state-of-the-art methods on synthetic and real-world text classification tasks. |
Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection (2025.acl-long)
Copied to clipboard
Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, Yangyang Kang
| Challenge: | Recent work utilizes feedbacks generated from erroneous cases to guide prompt optimization . previous methods rely on computational resources and powerful GPUs . |
| Approach: | They propose an automatic prompt engineering method that leverages feedbacks from erroneous cases to guide prompt optimization. |
| Outcome: | The proposed method surpasses state-of-the-art methods with less steps and lower computational resources. |
FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics (2025.coling-main)
Copied to clipboard
| Challenge: | Despite the success of fine-tuning Pre-trained Language Models, they remain susceptible to out-of-distribution input. |
| Approach: | They propose a novel approach that fine-tunes Pre-trained Language Models by transFerring Training dynamics (FTFT) FTFT uses more efficient reference models and aggressive early stopping . |
| Outcome: | The proposed approach improves the robustness of fine-tuned PLMs while reducing training costs. |
Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level (C18-1)
Copied to clipboard
| Challenge: | Emotion Representation Mapping (ERM) is an alternative to Word Emotion Induction (WEI) for automatic emotion lexicon construction. |
| Approach: | They propose a neural network approach to ERM that converts existing emotion ratings from one representation format into another by mapping Valence-Arousal-Dominance annotations into Ekman’s Basic Emotions. |
| Outcome: | The proposed model outperforms the state-of-the-art in 13 languages and is almost as reliable as human annotations even in cross-lingual settings. |
Mitigating Shortcut Learning with InterpoLated Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. |
| Approach: | They propose to interpolate representations of majority examples to include features from intra-class minority examples with shortcut-mitigating patterns. |
| Outcome: | The proposed method improves minority generalization over ERM and state-of-the-art mitigation methods on multiple natural language understanding tasks while preserving accuracy on majority examples. |
Learn from Failure: Causality-guided Contrastive Learning for Generalizable Implicit Hate Speech Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for detecting implicit hate speech rely on correlations between class labels and spurious attributes, which leads to poor performance on data lacking correlations. |
| Approach: | They propose a causality-guided contrastive learning approach to enhance the generalizability of implicit hate speech detection by aligning the representations of samples with the same class but opposite spurious attributes. |
| Outcome: | The proposed approach outperforms current state-of-the-art methods in cross-domain generalization on multiple implicit hate speech datasets. |
SAFO: Stable Adaptive Fairness Optimization for LLM-Based Social Survey Simulation (2026.acl-long)
Copied to clipboard
| Challenge: | Social survey simulations are increasingly used to improve minority performance and social-welfare metrics. |
| Approach: | They propose a dynamic utility–fairness optimization framework for LLM-based survey simulation that explicitly targets fairness and training stability. |
| Outcome: | The proposed framework improves minority performance and social-welfare metrics on three large-scale survey datasets from China, the U.S. and Europe. |