{"slug": "emolasp-emotion-recognition-with-language-models-and-answer-set-programming", "title": "EmoLASP: Emotion Recognition with Language Models and Answer Set Programming", "summary": "Researchers propose EmoLASP, a framework combining language models with Answer Set Programming to predict VAD scores in conversations, improving performance over using language models alone on the IEMOCAP benchmark across six open-source LLMs (3B-120B) and two PLMs (BERT, RoBERTa). The gains are largest for prompt-only LLMs without fine-tuning, while fine-tuned PLMs benefit little once dialogue history is available.", "body_md": "arXiv:2608.29035v1 Announce Type: new\nAbstract: Emotion recognition in conversations is increasingly tackled with language models, but these models can be unstable and expensive to fine-tune or to prompt with long dialogue histories. We propose EmoLASP, a framework that combines a language model with declarative reasoning via Answer Set Programming (ASP) to predict VAD scores (Valence-Arousal-Dominance) in conversations. Experiments on a widely used benchmark dataset (IEMOCAP) across six open-source LLMs (3B-120B) and two PLMs (BERT, RoBERTa) show that EmoLASP improves prediction performance compared to using the language model alone, even when the LLMs/PLMs are given no dialogue history in their prompts or input vectors. The gains are largest for prompt-only LLMs, which EmoLASP uses without any fine-tuning. However, for fine-tuned PLMs, the reasoner adds little once dialogue history is available. EmoLASP's LLM pipeline demonstrates the potential advantages of using a reasoning approach to ensure emotion prediction consistency and to reduce both the cost of fine-tuning and the cost of prompting with long dialogue histories.", "url": "https://wpnews.pro/news/emolasp-emotion-recognition-with-language-models-and-answer-set-programming", "canonical_source": "https://www.machinebrief.com/news/emolasp-emotion-recognition-with-language-models-and-answer-aoeo", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 06:53:20.260330+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research"], "entities": ["EmoLASP", "IEMOCAP", "BERT", "RoBERTa"], "alternates": {"html": "https://wpnews.pro/news/emolasp-emotion-recognition-with-language-models-and-answer-set-programming", "markdown": "https://wpnews.pro/news/emolasp-emotion-recognition-with-language-models-and-answer-set-programming.md", "text": "https://wpnews.pro/news/emolasp-emotion-recognition-with-language-models-and-answer-set-programming.txt", "jsonld": "https://wpnews.pro/news/emolasp-emotion-recognition-with-language-models-and-answer-set-programming.jsonld"}}