Papers with SAFE
ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis (2026.findings-acl)
Copied to clipboard
| Challenge: | Text-to-image (T2I) models are trained on literal, object-centric prompts designed to reflect the visible contents of an image. |
| Approach: | They propose a method to extract key subjects and enhance their representation at embedding-level using Large Language Models. |
| Outcome: | The proposed model significantly improves image-caption consistency and human preference alignment. |
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent improvements in NLP tasks can be attributed to the Transformer model. |
| Approach: | They propose to use parameter-sharing methods to reduce parameter budgets in generative models by using sandwich-style parameter sharing and self-attentive embedding factorization. |
| Outcome: | The proposed model outperforms the current RNN model even with significantly fewer parameters. |
Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models impose substantial resource usage. |
| Approach: | They propose a parameter-efficient fine-tuning method that freezes adapters early to reduce resource usage while maintaining performance. |
| Outcome: | The proposed method reduces memory usage, computation amount, and training time by 42.85%, 34.59%, and 11.82% while maintaining performance. |
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models suffer from hallucinations, which can undermine their performance in critical applications. |
| Approach: | They propose a framework for detecting and mitigating hallucinations by leveraging SAEs. |
| Outcome: | The proposed framework improves query generation accuracy and mitigates hallucinations across datasets. |
SAFE: Schema-Driven Approximate Distance Join for Efficient Knowledge Graph Querying (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods map an LLM-generated query graph onto the KG or let the LLM traverse the entire graph. |
| Approach: | They propose a framework that leverages schema graphs for robust query graph generation and efficient KG retrieval. |
| Outcome: | Extensive experiments on WebQSP, CWQ and GrailQA show that the proposed framework outperforms state-of-the-art methods in accuracy and efficiency. |