Models Detect Impossible Questions but Answer Anyway

Also Worth Noting

• CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions score 4
  关键词(2): agentic, reasoning; 顶会接收: EMNLP
• EmoLASP: Emotion Recognition with Language Models and Answer Set Programming score 4
  关键词(4): fine-tuning, fine-tune, reasoning, open-source; 顶会接收: EMNLP
• Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions score 4
  关键词(1): pretraining; 顶会接收: EMNLP
• Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages score 4
  关键词(1): lightweight; 顶会接收: EMNLP
• Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning score 4
  关键词(7): deployment, production, serving, latency, fine-tuning; 顶会接收: EMNLP
• Co-Evolutionary Prompt Optimization with Cross-Category Transfer for Zero-Shot Anomaly Detection score 4
  关键词(1): vision-language; 顶会接收: EMNLP
• Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction score 3
  顶会接收: EMNLP
• A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges score 3
  顶会接收: EMNLP
• STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation score 3
  顶会接收: ECCV
• How Identity and Opinion Shape Political Sycophancy in LLMs score 3
  顶会接收: EMNLP
• Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation score 3
  顶会接收: EMNLP