arXiv subjects

Amine Trabelsi

Publications and source records attributed to Amine Trabelsi.

16 recordsLinked to original sources

arXiv2026

Exposing Weaknesses in Emotion Recognition in Conversations

Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide range of applications, including empathetic conversational agents, mental health support, and educational technologies. While many recent approaches rely on task-specific fine-tuning, such models may exploit dataset-specific cues. A central yet rarely questioned assumption in ERC is that each utterance can be assigned a single unambiguous emotion label. To investigate this assumption, we study ERC using Large Language Models (LLMs) in a zero-shot setting while incorporating preceding conversational turns as context. We show that aggregate metrics mask systematic failures. Errors concentrate around utterances containing negations, exclamations, and interjections. This pattern is consistent across all evaluated models, suggesting limitations in the benchmarks rather than model-specific weaknesses. A controlled re-annotation study involving four human annotators supports this finding: strong agreement is observed in only 35 percent of cases, with neutral utterances dominating high-agreement instances, while many emotional categories fall into low-agreement regimes. These findings suggest that many apparent model errors reflect genuine annotation ambiguity rather than poor emotion understanding. Standard single-label evaluation is therefore insufficient. To address this limitation, we introduce an LLM-as-Judge framework that evaluates each emotion independently according to its plausibility in the conversational context rather than enforcing a single-label decision.

cs.AI↗

arXiv2026

Can temporal article-level credibility signals improve domain-level credibility prediction?

Web domain credibility evaluation is vital for combating misinformation. It is conducted by examining factors such as domain type, transparency, and overall reputation. However, assessing the credibility of newly emerging web domains remains challenging since they have no reputation yet. Expert fact-checkers evaluate the credibility of domains by analyzing the content of their articles, including the presence of misinformation, bias, or propaganda. Yet, the ease of large-scale content generation enabled by LLMs has accelerated the creation of new content, rendering manual assessment insufficient and underscoring the need for automated approaches to domain credibility evaluation. In this paper, we introduce our Domain Credibility Evaluation Framework (DCEF), a temporal framework for domain credibility evaluation grounded in expert ratings. DCEF enables us to investigate whether the credibility of web domains can be assessed from their published articles following the workflow of expert fact-checkers, without any prior knowledge of the source domains themselves.

cs.CL↗

arXiv2026

CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction

With the vast amount of content uploaded every hour, along with the AI generated content that can include hallucinations, Automated Fact-Checking (AFC) has become increasingly vital, as it is infeasible for human fact-checkers to manually verify the sheer volume of information generated online. Professional fact-checkers have identified several gaps in existing AFC systems, noting a misalignment between how these systems operate and how fact-checking is performed in practice. In this paper, we introduce CAAFC (Chronological Actionable Automated Fact-Checker), a frame-work designed to bridge these gaps. It surpasses SOTA AFC and hallucination detection systems across multiple benchmark datasets. CAAFC operates on claims, conversations, and dialogues, enabling it not only to detect factual errors and hallucinations, but also to correct them by providing actionable justifications supported by primary information sources. Furthermore, CAAFC can update evidence and knowledge bases by incorporating recent and contextual information when necessary, thereby enhancing the reliability of fact verification.

cs.AI↗

arXiv2025

Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?

Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as hateful speech detection or sentiment analysis. Surprisingly, the evaluation of this kind of bias in stance detection methods has been largely overlooked by the community. Stance Detection involves labeling a statement as being against, in favor, or neutral towards a specific target and is among the most sensitive NLP tasks, as it often relates to political leanings. In this paper, we focus on the bias of Large Language Models when performing stance detection in a zero-shot setting. We automatically annotate posts in pre-existing stance detection datasets with two attributes: dialect or vernacular of a specific group and text complexity/readability, to investigate whether these attributes influence the model's stance detection decisions. Our results show that LLMs exhibit significant stereotypes in stance detection tasks, such as incorrectly associating pro-marijuana views with low text complexity and African American dialect with opposition to Donald Trump.

cs.CL↗

arXiv2025

Can Large Language Models Address Open-Target Stance Detection?

Stance detection (SD) identifies the text position towards a target, typically labeled as favor, against, or none. We introduce Open-Target Stance Detection (OTSD), the most realistic task where targets are neither seen during training nor provided as input. We evaluate Large Language Models (LLMs) from GPT, Gemini, Llama, and Mistral families, comparing their performance to the only existing work, Target-Stance Extraction (TSE), which benefits from predefined targets. Unlike TSE, OTSD removes the dependency of a predefined list, making target generation and evaluation more challenging. We also provide a metric for evaluating target quality that correlates well with human judgment. Our experiments reveal that LLMs outperform TSE in target generation, both when the real target is explicitly and not explicitly mentioned in the text. Similarly, LLMs overall surpass TSE in stance detection for both explicit and non-explicit cases. However, LLMs struggle in both target generation and stance detection when the target is not explicit.

cs.CL↗

arXiv2025

FinGrAct: A Framework for FINe-GRrained Evaluation of ACTionability in Explainable Automatic Fact-Checking

The field of explainable Automatic Fact-Checking (AFC) aims to enhance the transparency and trustworthiness of automated fact-verification systems by providing clear and comprehensible explanations. However, the effectiveness of these explanations depends on their actionability --their ability to empower users to make informed decisions and mitigate misinformation. Despite actionability being a critical property of high-quality explanations, no prior research has proposed a dedicated method to evaluate it. This paper introduces FinGrAct, a fine-grained evaluation framework that can access the web, and it is designed to assess actionability in AFC explanations through well-defined criteria and an evaluation dataset. FinGrAct surpasses state-of-the-art (SOTA) evaluators, achieving the highest Pearson and Kendall correlation with human judgments while demonstrating the lowest ego-centric bias, making it a more robust evaluation approach for actionability evaluation in AFC.

cs.AI↗

arXiv2024

Recent Trends in Unsupervised Summarization

Unsupervised summarization is a powerful technique that enables training summarizing models without requiring labeled datasets. This survey covers different recent techniques and models used for unsupervised summarization. We cover extractive, abstractive, and hybrid models and strategies used to achieve unsupervised summarization. While the main focus of this survey is on recent research, we also cover some of the important previous research. We additionally introduce a taxonomy, classifying different research based on their approach to unsupervised training. Finally, we discuss the current approaches and mention some datasets and evaluation methods.

cs.CL↗

arXiv2024

Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approaches

Automated Fact-Checking (AFC) is the automated verification of claim accuracy. AFC is crucial in discerning truth from misinformation, especially given the huge amounts of content are generated online daily. Current research focuses on predicting claim veracity through metadata analysis and language scrutiny, with an emphasis on justifying verdicts. This paper surveys recent methodologies, proposing a comprehensive taxonomy and presenting the evolution of research in that landscape. A comparative analysis of methodologies and future directions for improving fact-checking explainability are also discussed.

cs.CL↗

arXiv2024

Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric

The proliferation of social media platforms has given rise to the amount of online debates and arguments. Consequently, the need for automatic summarization methods for such debates is imperative, however this area of summarization is rather understudied. The Key Point Analysis (KPA) task formulates argument summarization as representing the summary of a large collection of arguments in the form of concise sentences in bullet-style format, called key points. A sub-task of KPA, called Key Point Generation (KPG), focuses on generating these key points given the arguments. This paper introduces a novel extractive approach for key point generation, that outperforms previous state-of-the-art methods for the task. Our method utilizes an extractive clustering based approach that offers concise, high quality generated key points with higher coverage of reference summaries, and less redundant outputs. In addition, we show that the existing evaluation metrics for summarization such as ROUGE are incapable of differentiating between generated key points of different qualities. To this end, we propose a new evaluation metric for assessing the generated key points by their coverage. Our code can be accessed online.

cs.CL↗

arXiv2022

FREDA: Flexible Relation Extraction Data Annotation

To effectively train accurate Relation Extraction models, sufficient and properly labeled data is required. Adequately labeled data is difficult to obtain and annotating such data is a tricky undertaking. Previous works have shown that either accuracy has to be sacrificed or the task is extremely time-consuming, if done accurately. We are proposing an approach in order to produce high-quality datasets for the task of Relation Extraction quickly. Neural models, trained to do Relation Extraction on the created datasets, achieve very good results and generalize well to other datasets. In our study, we were able to annotate 10,022 sentences for 19 relations in a reasonable amount of time, and trained a commonly used baseline model for each relation.

cs.CL↗

arXiv2022

Named Entity Recognition for Partially Annotated Datasets

The most common Named Entity Recognizers are usually sequence taggers trained on fully annotated corpora, i.e. the class of all words for all entities is known. Partially annotated corpora, i.e. some but not all entities of some types are annotated, are too noisy for training sequence taggers since the same entity may be annotated one time with its true type but not another time, misleading the tagger. Therefore, we are comparing three training strategies for partially annotated datasets and an approach to derive new datasets for new classes of entities from Wikipedia without time-consuming manual data annotation. In order to properly verify that our data acquisition and training approaches are plausible, we manually annotated test datasets for two new classes, namely food and drugs.

cs.CL↗

arXiv2020

ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)

In this paper, we describe our mUlti-task learNIng for cOmmonsense reasoNing (UNION) system submitted for Task C of the SemEval2020 Task 4, which is to generate a reason explaining why a given false statement is non-sensical. However, we found in the early experiments that simple adaptations such as fine-tuning GPT2 often yield dull and non-informative generations (e.g. simple negations). In order to generate more meaningful explanations, we propose UNION, a unified end-to-end framework, to utilize several existing commonsense datasets so that it allows a model to learn more dynamics under the scope of commonsense reasoning. In order to perform model selection efficiently, accurately and promptly, we also propose a couple of auxiliary automatic evaluation metrics so that we can extensively compare the models from different perspectives. Our submitted system not only results in a good performance in the proposed metrics but also outperforms its competitors with the highest achieved score of 2.10 for human evaluation while remaining a BLEU score of 15.7. Our code is made publicly available at GitHub.

cs.CL↗

arXiv2019

Seq2Emo for Multi-label Emotion Classification Based on Latent Variable Chains Transformation

Emotion detection in text is an important task in NLP and is essential in many applications. Most of the existing methods treat this task as a problem of single-label multi-class text classification. To predict multiple emotions for one instance, most of the existing works regard it as a general Multi-label Classification (MLC) problem, where they usually either apply a manually determined threshold on the last output layer of their neural network models or train multiple binary classifiers and make predictions in the fashion of one-vs-all. However, compared to labels in the general MLC datasets, the number of emotion categories are much fewer (less than 10). Additionally, emotions tend to have more correlations with each other. For example, the human usually does not express "joy" and "anger" at the same time, but it is very likely to have "joy" and "love" expressed together. Given this intuition, in this paper, we propose a Latent Variable Chain (LVC) transformation and a tailored model -- Seq2Emo model that not only naturally predicts multiple emotion labels but also takes into consideration their correlations. We perform the experiments on the existing multi-label emotion datasets as well as on our newly collected datasets. The results show that our model compares favorably with existing state-of-the-art methods.

cs.CL↗

arXiv2019

Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems

Self-attentional models are a new paradigm for sequence modelling tasks which differ from common sequence modelling methods, such as recurrence-based and convolution-based sequence learning, in the way that their architecture is only based on the attention mechanism. Self-attentional models have been used in the creation of the state-of-the-art models in many NLP tasks such as neural machine translation, but their usage has not been explored for the task of training end-to-end task-oriented dialogue generation systems yet. In this study, we apply these models on the three different datasets for training task-oriented chatbots. Our finding shows that self-attentional models can be exploited to create end-to-end task-oriented chatbots which not only achieve higher evaluation scores compared to recurrence-based models, but also do so more efficiently.

cs.CL↗

arXiv2019

Contrastive Reasons Detection and Clustering from Online Polarized Debate

This work tackles the problem of unsupervised modeling and extraction of the main contrastive sentential reasons conveyed by divergent viewpoints on polarized issues. It proposes a pipeline approach centered around the detection and clustering of phrases, assimilated to argument facets using a novel Phrase Author Interaction Topic-Viewpoint model. The evaluation is based on the informativeness, the relevance and the clustering accuracy of extracted reasons. The pipeline approach shows a significant improvement over state-of-the-art methods in contrastive summarization on online debate datasets.

cs.CL↗

arXiv2019

ANA at SemEval-2019 Task 3: Contextual Emotion detection in Conversations through hierarchical LSTMs and BERT

This paper describes the system submitted by ANA Team for the SemEval-2019 Task 3: EmoContext. We propose a novel Hierarchical LSTMs for Contextual Emotion Detection (HRLCE) model. It classifies the emotion of an utterance given its conversational context. The results show that, in this task, our HRCLE outperforms the most recent state-of-the-art text classification framework: BERT. We combine the results generated by BERT and HRCLE to achieve an overall score of 0.7709 which ranked 5th on the final leader board of the competition among 165 Teams.

cs.CL↗