TweetEval
PulseAugur coverage of TweetEval — every cluster mentioning TweetEval across labs, papers, and developer communities, ranked by signal.
-
New research explores modular and recursive methods for automatic prompt optimization
Two new research papers introduce novel methods for optimizing prompts used with large language models. The first, SAPO, breaks down prompts into segments like role, context, and task, allowing for targeted improvements…
-
New AI framework boosts irony detection in social media
Researchers have developed a novel framework called Robust Dual-Signal (RDS) Fusion to improve irony detection in social media texts, a task that challenges standard Large Language Models (LLMs). The hybrid neuro-symbol…
-
LLM Annotators Show Social-Desirability Bias in Social Science Research
A new paper investigates social-desirability bias in LLM annotators used for computational social science. Researchers found that three open-source models (Zephyr, Mistral-Instruct, and Qwen2.5-Instruct) exhibit differe…