The 2025 Conference on Empirical Methods in Natural Language Processing
PulseAugur coverage of The 2025 Conference on Empirical Methods in Natural Language Processing — every cluster mentioning The 2025 Conference on Empirical Methods in Natural Language Processing across labs, papers, and developer communities, ranked by signal.
-
Local LLM measurements reveal issues with 'thinking' and self-critique
Running local LLMs like Qwen3.5 4B requires careful measurement and verification, as results can be inconsistent. Enabling 'thinking' in some models can lead to empty responses if the token budget is exceeded, necessita…
-
EMNLP 2025 Checklist Analysis Reveals Superficial Compliance with Responsible NLP
A new analysis of the EMNLP 2025 conference revealed significant issues with the Responsible NLP Checklist, suggesting it may be a superficial exercise rather than a driver of genuine ethical consideration. Researchers …
-
Google AI uses small models for superior intent extraction
Google AI researchers have developed a novel method for understanding user intents from UI interaction trajectories using small multimodal large language models (MLLMs). This approach decomposes the task into two stages…