SEER: The Span-based Emotion Evidence Retrieval Benchmark

• URL: http://arxiv.org/abs/2510.03490v2
• Date: Tue, 28 Oct 2025 01:07:57 GMT
• Title: SEER: The Span-based Emotion Evidence Retrieval Benchmark
• Authors: Aneesha Sampath, Oya Aran, Emily Mower Provost,
• Abstract summary: We introduce the SEER (Span-based Emotion Evidence Retrieval) Benchmark to test Large Language Models' ability to identify the specific spans of text that express emotion.<n>We evaluate 14 open-source LLMs and find that, while some models approach average human performance on single-sentence inputs, their accuracy degrades in longer passages.
• Score: 8.124633573706761
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce the SEER (Span-based Emotion Evidence Retrieval) Benchmark to test Large Language Models' (LLMs) ability to identify the specific spans of text that express emotion. Unlike traditional emotion recognition tasks that assign a single label to an entire sentence, SEER targets the underexplored task of emotion evidence detection: pinpointing which exact phrases convey emotion. This span-level approach is crucial for applications like empathetic dialogue and clinical support, which need to know how emotion is expressed, not just what the emotion is. SEER includes two tasks: identifying emotion evidence within a single sentence, and identifying evidence across a short passage of five consecutive sentences. It contains new annotations for both emotion and emotion evidence on 1200 real-world sentences. We evaluate 14 open-source LLMs and find that, while some models approach average human performance on single-sentence inputs, their accuracy degrades in longer passages. Our error analysis reveals key failure modes, including overreliance on emotion keywords and false positives in neutral text.

Related papers

• Empaths at SemEval-2025 Task 11: Retrieval-Augmented Approach to Perceived Emotions Prediction [83.88591755871734]
  EmoRAG is a system designed to detect perceived emotions in text for SemEval-2025 Task 11, Subtask A: Multi-label Emotion Detection.<n>We focus on predicting the perceived emotions of the speaker from a given text snippet, labeling it with emotions such as joy, sadness, fear, anger, surprise, and disgust.
  arXiv  Detail & Related papers  (2025-06-04T19:41:24Z)
• UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech [61.989360995528905]
  We propose UDDETTS, a universal framework unifying discrete and dimensional emotions for controllable emotional TTS.<n>This model introduces the interpretable Arousal-Dominance-Valence (ADV) space for dimensional emotion description and supports emotion control driven by either discrete emotion labels or nonlinearly quantified ADV values.<n>Experiments show that UDDETTS achieves linear emotion control along three interpretable dimensions, and exhibits superior end-to-end emotional speech synthesis capabilities.
  arXiv  Detail & Related papers  (2025-05-15T12:57:19Z)
• Towards a Generative Approach for Emotion Detection and Reasoning [0.7366405857677227]
  We introduce a novel approach to zero-shot emotion detection and emotional reasoning using large language models. Our paper is the first work on using a generative approach to jointly address the tasks of emotion detection and emotional reasoning for texts.
  arXiv  Detail & Related papers  (2024-08-09T07:20:15Z)
• Think out Loud: Emotion Deducing Explanation in Dialogues [57.90554323226896]
  We propose a new task "Emotion Deducing Explanation in Dialogues" (EDEN) EDEN recognizes emotion and causes in an explicitly thinking way. It can help Large Language Models (LLMs) achieve better recognition of emotions and causes.
  arXiv  Detail & Related papers  (2024-06-07T08:58:29Z)
• Dynamic Causal Disentanglement Model for Dialogue Emotion Detection [77.96255121683011]
  We propose a Dynamic Causal Disentanglement Model based on hidden variable separation. This model effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions. Specifically, we propose a dynamic temporal disentanglement model to infer the propagation of utterances and hidden variables.
  arXiv  Detail & Related papers  (2023-09-13T12:58:09Z)
• Experiencer-Specific Emotion and Appraisal Prediction [13.324006587838523]
  Emotion classification in NLP assigns emotions to texts, such as sentences or paragraphs. We focus on the experiencers of events, and assign an emotion (if any holds) to each of them. Our experiencer-aware models of emotions and appraisals outperform the experiencer-agnostic baselines.
  arXiv  Detail & Related papers  (2022-10-21T16:04:27Z)
• CEFER: A Four Facets Framework based on Context and Emotion embedded features for Implicit and Explicit Emotion Recognition [2.5137859989323537]
  We propose a framework that analyses text at both the sentence and word levels. We name it CEFER (Context and Emotion embedded Framework for Emotion Recognition) CEFER combines the emotional vector of each word, including explicit and implicit emotions, with the feature vector of each word based on context.
  arXiv  Detail & Related papers  (2022-09-28T11:16:32Z)
• Speech Synthesis with Mixed Emotions [77.05097999561298]
  We propose a novel formulation that measures the relative difference between the speech samples of different emotions. We then incorporate our formulation into a sequence-to-sequence emotional text-to-speech framework. At run-time, we control the model to produce the desired emotion mixture by manually defining an emotion attribute vector.
  arXiv  Detail & Related papers  (2022-08-11T15:45:58Z)
• Uncovering the Limits of Text-based Emotion Detection [0.0]
  We consider the two largest corpora for emotion classification: GoEmotions, with 58k messages labelled by readers, and Vent, with 33M writer-labelled messages. We design a benchmark and evaluate several feature spaces and learning algorithms, including two simple yet novel models on top of BERT.
  arXiv  Detail & Related papers  (2021-09-04T16:40:06Z)
• A Circular-Structured Representation for Visual Emotion Distribution Learning [82.89776298753661]
  We propose a well-grounded circular-structured representation to utilize the prior knowledge for visual emotion distribution learning. To be specific, we first construct an Emotion Circle to unify any emotional state within it. On the proposed Emotion Circle, each emotion distribution is represented with an emotion vector, which is defined with three attributes.
  arXiv  Detail & Related papers  (2021-06-23T14:53:27Z)
• SpanEmo: Casting Multi-label Emotion Classification as Span-prediction [15.41237087996244]
  We propose a new model "SpanEmo" casting multi-label emotion classification as span-prediction. We introduce a loss function focused on modelling multiple co-existing emotions in the input sentence. Experiments performed on the SemEval2018 multi-label emotion data over three language sets demonstrate our method's effectiveness.
  arXiv  Detail & Related papers  (2021-01-25T12:11:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.