GoEmotions: A Dataset of Fine-Grained Emotions
PulseAugur coverage of GoEmotions: A Dataset of Fine-Grained Emotions — every cluster mentioning GoEmotions: A Dataset of Fine-Grained Emotions across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
LLMs show "overcompression" of fine-grained emotions in representations
Researchers have investigated how large language models (LLMs) internally represent emotions, using the GoEmotions dataset which contains 27 fine-grained emotion categories. Their findings indicate a consistent pattern …
-
New NLP research analyzes disagreement structures in emotion annotation
A new paper published on arXiv explores the structure of disagreement in emotion annotation within natural language processing. The research analyzes multilabel annotations from three datasets, including Ernest Hemingwa…
-
New method boosts LLM emotion reasoning using internal attention signals
Researchers have developed a new method called Self-targeted Internal Attention Boosting (SIAB) to help large language models (LLMs) better reason about affective states, such as emotions, within conversations. Unlike p…
-
Emotion labels vary significantly across datasets, study finds
A new research paper challenges the assumption that emotion labels like 'fear' or 'surprise' are consistently interpreted across different datasets. The study found significant variations in how emotion classifiers labe…
-
New PGCL method improves evaluation of AI-generated text
Researchers have developed a new method called Prototype-Guided Contrastive Learning (PGCL) to improve the evaluation of generated text. This approach works with frozen text embeddings, meaning the base model is not upd…
-
New method uses discrete diffusion models for training-free multi-label text classification
Researchers have introduced dLLM-SetScore, a novel method that leverages discrete masked-diffusion language models for multi-label text classification without requiring task-specific fine-tuning. This approach involves …
-
New framework BACE quantifies emotion recognition predictability limits
Researchers have developed a new framework called Bias-Corrected Affective Ceiling Estimation (BACE) to better understand the predictability limits of emotion recognition from text. This method aims to quantify how fact…
-
FLARE framework optimizes LLM instructions, outperforming GEPA
Researchers have introduced FLARE, a new framework designed to optimize instructions for large language models. FLARE utilizes advanced reflective mechanisms and a limited set of few-shot reference examples to enhance p…
-
FLARE framework outperforms GEPA in optimizing LLM instructions
Researchers have introduced FLARE, a new framework for optimizing instructions in large language models. FLARE utilizes reflective mechanisms and a small set of few-shot examples to improve performance across various be…
-
New frameworks boost LLM agents' negotiation skills with emotional strategies
Researchers have developed two new frameworks, EmoDistill and EvoEmo, to enhance the negotiation capabilities of language model agents by incorporating emotional strategies. EmoDistill focuses on distilling emotional ne…
-
New NLP method decomposes uncertainty using soft-label learning
Researchers have developed a novel method for decomposing uncertainty in subjective Natural Language Processing tasks, specifically emotion classification. This approach combines cyclical stochastic gradient Markov chai…
-
AI models struggle with emotion nuance, researchers explore new evaluation and generation methods
Researchers are exploring the nuances of emotion in AI, with several papers focusing on Large Language Models (LLMs) and speech processing. One study investigates how well small language models preserve emotions during …