arXiv subjects

Paul Buitelaar

Publications and source records attributed to Paul Buitelaar.

At least 19 recordsLinked to original sources

arXiv2026

Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems

Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs). Although various mitigation approaches have been proposed, existing studies often analyze different technical paradigms independently, lacking a unified perspective to understand the underlying mechanisms of different approaches and their correspondence with different types of hallucinations. This survey adopts a capability enhancement perspective to systematically examine hallucination mitigation approaches, focusing on Retrieval-Augmented Generation (RAG), reasoning enhancement, and their integration within agentic systems. Based on their primary mitigation mechanisms, we categorize hallucinations into knowledge-based hallucinations and logic-based hallucinations, analyze how RAG and reasoning enhancement methods respectively improve knowledge acquisition and reasoning reliability, and further discuss the integration mechanisms of retrieval and reasoning capabilities in Agentic Systems for mitigating composite hallucinations. By considering the applicability, mitigation mechanisms, and limitations of different approaches, this survey establishes a unified analytical framework connecting hallucination types, key capability dimensions, and technical paradigms.

cs.CL↗

arXiv2026

KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs

Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly in domain-specific contexts where general-purpose LLMs and RAG tend to underperform. We hypothesize that augmenting RAG with unstructured and structured knowledge, extracted from both documents and knowledge graphs (KGs), can improve reasoning and answer accuracy for such tasks. To test this, we propose KGCaRe, a hybrid approach that combines neural retrieval with symbolic reasoning over LLM-generated KGs. KGCaRe constructs a KG from documents using a multi-prompt extraction strategy and stores it in a graph database. Simultaneously, the documents are embedded into a vector store to enable neural retrieval. KGCaRe performs innovative iterative graph traversal guided by the LLM to extract relevant triples, prune irrelevant information, and uses additional clue entities to traverse the graph again if the initial traversal does not provide satisfactory context to generate the answer. The relevant triples extracted from the KG in path form, along with semantically retrieved text passages, are then fed into custom KGCaRe prompts to generate answers to the complex conditional questions with explanations. We evaluate KGCaRe on two complex conditional QA datasets. Our results on these datasets show that KGCaRe consistently outperforms existing baselines, including Vanilla LLM, Code Prompt, Text Prompt, Think-on-Graph, Vanilla RAG, and HybridContextQA, across multiple LLMs such as Mistral, Mixtral, GPT-3.5, and GPT-4o. We publicly release the software pipeline that we developed to implement the proposed KGCaRe approach.

cs.CL↗

arXiv2026

Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis

Fine-grained opinion analysis of text provides a detailed understanding of expressed sentiments and their targets. Although this level of detail is valuable, annotating opinions in datasets for model training requires considerable human effort and substantial cost, especially across diverse domains and real-world applications. To address this shortage of domain-specific labelled datasets, we explore the feasibility of LLMs as automatic annotators for fine-grained opinion analysis. We use a declarative annotation pipeline, an approach that reduces the variability of manual prompt engineering when using LLMs to identify fine-grained opinion spans in text. We also present a dedicated methodology for an LLM to adjudicate multiple labels and produce final annotations, benchmarked against exact, flexible, and element-wise variants of a rule-based voting aggregator. We trial the pipeline with models of different sizes for the Aspect Sentiment Triplet Extraction (ASTE) and Aspect-Category-Opinion-Sentiment (ACOS) analysis tasks. Our results reveal a critical performance bifurcation: LLMs are reliable at the span level yet struggle to reproduce the relational structures that connect those spans faithfully. This suggests that LLMs are better positioned as high-fidelity annotation assistants and data augmentation tools to expand fine-grained opinion-annotated datasets, rather than replacing human annotators entirely.

cs.CL↗

arXiv2026

Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach

While sentiment analysis is the staple of financial NLP, capturing the nuances of 'why' behind that sentiment remains a challenge. There have been attempts to address this by analysing investor emotions alongside sentiment; however, this does not provide the additional granularity required to understand the target of the emotion/sentiment. We address this by augmenting the StockEmotions dataset with semantically structured opinion graphs, which provide granular semantic depth to the existing sentiment and emotion labels. Using a declarative LLM pipeline, we augment the StockEmotions dataset with opinion graphs for each sentence, derived from 10,000 comments collected from StockTwits. In addition, we study the effect of introducing opinion semantics on baseline classifiers using Graph Neural Networks (GNNs). Our analysis demonstrates that incorporating opinion semantics improves classification performance across different emotional spectrums

cs.CL↗

arXiv2025

A Progressive Evaluation Framework for Multicultural Analysis of Story Visualization

Recent advancements in text-to-image generative models have improved narrative consistency in story visualization. However, current story visualization models often overlook cultural dimensions, resulting in visuals that lack authenticity and cultural fidelity. In this study, we conduct a comprehensive multicultural analysis of story visualization using current text-to-image models across multilingual settings on two datasets: FlintstonesSV and VIST. To assess cultural dimensions rigorously, we propose a Progressive Multicultural Evaluation Framework and introduce five story visualization metrics, Cultural Appropriateness, Visual Aesthetics, Cohesion, Semantic Consistency, and Object Presence, that are not addressed by existing metrics. We further automate assessment through an MLLM-as-Jury framework that approximates human judgment. Human evaluations show that models generate more coherent, visually appealing, and culturally appropriate stories for real-world datasets than for animated ones. The generated stories exhibit a stronger alignment with English-speaking cultures across all metrics except Cohesion, where Chinese performs better. In contrast, Hindi ranks lowest on all metrics except Visual Aesthetics, reflecting real-world cultural biases embedded in current models. This multicultural analysis provides a foundation for future research aimed at generating culturally appropriate and inclusive visual stories across diverse linguistic and cultural settings.

cs.MM↗

arXiv2025

Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models

We propose a scalable method for constructing a temporal opinion knowledge base with large language models (LLMs) as automated annotators. Despite the demonstrated utility of time-series opinion analysis of text for downstream applications such as forecasting and trend analysis, existing methodologies underexploit this potential due to the absence of temporally grounded fine-grained annotations. Our approach addresses this gap by integrating well-established opinion mining formulations into a declarative LLM annotation pipeline, enabling structured opinion extraction without manual prompt engineering. We define three data models grounded in sentiment and opinion mining literature, serving as schemas for structured representation. We perform rigorous quantitative evaluation of our pipeline using human-annotated test samples. We carry out the final annotations using two separate LLMs, and inter-annotator agreement is computed label-wise across the fine-grained opinion dimensions, analogous to human annotation protocols. The resulting knowledge base encapsulates time-aligned, structured opinions and is compatible with applications in Retrieval-Augmented Generation (RAG), temporal question answering, and timeline summarisation.

cs.CL↗

arXiv2025

Towards Semantic Integration of Opinions: Unified Opinion Concepts Ontology and Extraction Task

This paper introduces the Unified Opinion Concepts (UOC) ontology to integrate opinions within their semantic context. The UOC ontology bridges the gap between the semantic representation of opinion across different formulations. It is a unified conceptualisation based on the facets of opinions studied extensively in NLP and semantic structures described through symbolic descriptions. We further propose the Unified Opinion Concept Extraction (UOCE) task of extracting opinions from the text with enhanced expressivity. Additionally, we provide a manually extended and re-annotated evaluation dataset for this task and tailored evaluation metrics to assess the adherence of extracted opinions to UOC semantics. Finally, we establish baseline performance for the UOCE task using state-of-the-art generative models.

cs.CL↗

arXiv2025

Inference to the Best Explanation in Large Language Models

While Large Language Models (LLMs) have found success in real-world applications, their underlying explanatory process is still poorly understood. This paper proposes IBE-Eval, a framework inspired by philosophical accounts on Inference to the Best Explanation (IBE) to advance the interpretation and evaluation of LLMs' explanations. IBE-Eval estimates the plausibility of natural language explanations through a combination of explicit logical and linguistic features including: consistency, parsimony, coherence, and uncertainty. Extensive experiments are conducted on Causal Question Answering (CQA), where \textit{IBE-Eval} is tasked to select the most plausible causal explanation amongst competing ones generated by LLMs (i.e., GPT 3.5 and Llama 2). The experiments reveal that IBE-Eval can successfully identify the best explanation with up to 77\% accuracy ($\approx 27\%$ above random), improving upon a GPT 3.5-as-a-Judge baseline ($\approx+17\%$) while being intrinsically more efficient and interpretable. Additional analyses suggest that, despite model-specific variances, LLM-generated explanations tend to conform to IBE criteria and that IBE-Eval is significantly correlated with human judgment, opening up opportunities for future development of automated explanation verification tools.

cs.CL↗

arXiv2025

Empowering recommender systems using automatically generated Knowledge Graphs and Reinforcement Learning

Personalized recommender systems play a crucial role in direct marketing, particularly in financial services, where delivering relevant content can enhance customer engagement and promote informed decision-making. This study explores interpretable knowledge graph (KG)-based recommender systems by proposing two distinct approaches for personalized article recommendations within a multinational financial services firm. The first approach leverages Reinforcement Learning (RL) to traverse a KG constructed from both structured (tabular) and unstructured (textual) data, enabling interpretability through Path Directed Reasoning (PDR). The second approach employs the XGBoost algorithm, with post-hoc explainability techniques such as SHAP and ELI5 to enhance transparency. By integrating machine learning with automatically generated KGs, our methods not only improve recommendation accuracy but also provide interpretable insights, facilitating more informed decision-making in customer relationship management.

cs.IR↗

arXiv2024

A Hybrid Approach To Aspect Based Sentiment Analysis Using Transfer Learning

Aspect-Based Sentiment Analysis (ABSA) aims to identify terms or multiword expressions (MWEs) on which sentiments are expressed and the sentiment polarities associated with them. The development of supervised models has been at the forefront of research in this area. However, training these models requires the availability of manually annotated datasets which is both expensive and time-consuming. Furthermore, the available annotated datasets are tailored to a specific domain, language, and text type. In this work, we address this notable challenge in current state-of-the-art ABSA research. We propose a hybrid approach for Aspect Based Sentiment Analysis using transfer learning. The approach focuses on generating weakly-supervised annotations by exploiting the strengths of both large language models (LLM) and traditional syntactic dependencies. We utilise syntactic dependency structures of sentences to complement the annotations generated by LLMs, as they may overlook domain-specific aspect terms. Extensive experimentation on multiple datasets is performed to demonstrate the efficacy of our hybrid method for the tasks of aspect term extraction and aspect sentiment classification. Keywords: Aspect Based Sentiment Analysis, Syntactic Parsing, large language model (LLM)

cs.CL↗

arXiv2022

TrollsWithOpinion: A Dataset for Predicting Domain-specific Opinion Manipulation in Troll Memes

Research into the classification of Image with Text (IWT) troll memes has recently become popular. Since the online community utilizes the refuge of memes to express themselves, there is an abundance of data in the form of memes. These memes have the potential to demean, harras, or bully targeted individuals. Moreover, the targeted individual could fall prey to opinion manipulation. To comprehend the use of memes in opinion manipulation, we define three specific domains (product, political or others) which we classify into troll or not-troll, with or without opinion manipulation. To enable this analysis, we enhanced an existing dataset by annotating the data with our defined classes, resulting in a dataset of 8,881 IWT or multimodal memes in the English language (TrollsWithOpinion dataset). We perform baseline experiments on the annotated dataset, and our result shows that existing state-of-the-art techniques could only reach a weighted-average F1-score of 0.37. This shows the need for a development of a specific technique to deal with multimodal troll memes.

cs.SI↗

arXiv2020

Contextual Modulation for Relation-Level Metaphor Identification

Identifying metaphors in text is very challenging and requires comprehending the underlying comparison. The automation of this cognitive process has gained wide attention lately. However, the majority of existing approaches concentrate on word-level identification by treating the task as either single-word classification or sequential labelling without explicitly modelling the interaction between the metaphor components. On the other hand, while existing relation-level approaches implicitly model this interaction, they ignore the context where the metaphor occurs. In this work, we address these limitations by introducing a novel architecture for identifying relation-level metaphoric expressions of certain grammatical relations based on contextual modulation. In a methodology inspired by works in visual reasoning, our approach is based on conditioning the neural network computation on the deep contextualised features of the candidate expressions using feature-wise linear modulation. We demonstrate that the proposed architecture achieves state-of-the-art results on benchmark datasets. The proposed methodology is generic and could be applied to other textual classification problems that benefit from contextual interaction.

cs.CL↗

arXiv2019

Translating Terminological Expressions in Knowledge Bases with Neural Machine Translation

Our work presented in this paper focuses on the translation of terminological expressions represented in semantically structured resources, like ontologies or knowledge graphs. The challenge of translating ontology labels or terminological expressions documented in knowledge bases lies in the highly specific vocabulary and the lack of contextual information, which can guide a machine translation system to translate ambiguous words into the targeted domain. Due to these challenges, we evaluate the translation quality of domain-specific expressions in the medical and financial domain with statistical as well as with neural machine translation methods and experiment domain adaptation of the translation models with terminological expressions only. Furthermore, we perform experiments on the injection of external terminological expressions into the translation systems. Through these experiments, we observed a significant advantage in domain adaptation for the domain-specific resource in the medical and financial domain and the benefit of subword models over word-based neural machine translation models for terminology translation.

cs.CL↗

arXiv2019

Polylingual Wordnet

Princeton WordNet is one of the most important resources for natural language processing, but is only available for English. While it has been translated using the expand approach to many other languages, this is an expensive manual process. Therefore it would be beneficial to have a high-quality automatic translation approach that would support NLP techniques, which rely on WordNet in new languages. The translation of wordnets is fundamentally complex because of the need to translate all senses of a word including low frequency senses, which is very challenging for current machine translation approaches. For this reason we leverage existing translations of WordNet in other languages to identify contextual information for wordnet senses from a large set of generic parallel corpora. We evaluate our approach using 10 translated wordnets for European languages. Our experiment shows a significant improvement over translation without any contextual information. Furthermore, we evaluate how the choice of pivot languages affects performance of multilingual word sense disambiguation.

cs.CL↗

arXiv2019

Augmenting Neural Machine Translation with Knowledge Graphs

While neural networks have been used extensively to make substantial progress in the machine translation task, they are known for being heavily dependent on the availability of large amounts of training data. Recent efforts have tried to alleviate the data sparsity problem by augmenting the training data using different strategies, such as back-translation. Along with the data scarcity, the out-of-vocabulary words, mostly entities and terminological expressions, pose a difficult challenge to Neural Machine Translation systems. In this paper, we hypothesize that knowledge graphs enhance the semantic feature extraction of neural models, thus optimizing the translation of entities and terminological expressions in texts and consequently leading to a better translation quality. We hence investigate two different strategies for incorporating knowledge graphs into neural models without modifying the neural network architectures. We also examine the effectiveness of our augmentation method to recurrent and non-recurrent (self-attentional) neural architectures. Our knowledge graph augmented neural translation model, dubbed KG-NMT, achieves significant and consistent improvements of +3 BLEU, METEOR and chrF3 on average on the newstest datasets between 2014 and 2018 for WMT English-German translation task.

cs.CL↗

arXiv2018

Open Domain Suggestion Mining: Problem Definition and Datasets

We propose a formal definition for the task of suggestion mining in the context of a wide range of open domain applications. Human perception of the term \emph{suggestion} is subjective and this effects the preparation of hand labeled datasets for the task of suggestion mining. Existing work either lacks a formal problem definition and annotation procedure, or provides domain and application specific definitions. Moreover, many previously used manually labeled datasets remain proprietary. We first present an annotation study, and based on our observations propose a formal task definition and annotation procedure for creating benchmark datasets for suggestion mining. With this study, we also provide publicly available labeled datasets for suggestion mining in multiple domains.

cs.CL↗

arXiv2017

Inducing Distant Supervision in Suggestion Mining through Part-of-Speech Embeddings

Mining suggestion expressing sentences from a given text is a less investigated sentence classification task, and therefore lacks hand labeled benchmark datasets. In this work, we propose and evaluate two approaches for distant supervision in suggestion mining. The distant supervision is obtained through a large silver standard dataset, constructed using the text from wikiHow and Wikipedia. Both the approaches use a LSTM based neural network architecture to learn a classification model for suggestion mining, but vary in their method to use the silver standard dataset. The first approach directly trains the classifier using this dataset, while the second approach only learns word embeddings from this dataset. In the second approach, we also learn POS embeddings, which interestingly gives the best classification accuracy.

cs.CL↗

arXiv2017

Automatic Taxonomy Generation - A Use-Case in the Legal Domain

A key challenge in the legal domain is the adaptation and representation of the legal knowledge expressed through texts, in order for legal practitioners and researchers to access this information easier and faster to help with compliance related issues. One way to approach this goal is in the form of a taxonomy of legal concepts. While this task usually requires a manual construction of terms and their relations by domain experts, this paper describes a methodology to automatically generate a taxonomy of legal noun concepts. We apply and compare two approaches on a corpus consisting of statutory instruments for UK, Wales, Scotland and Northern Ireland laws.

cs.AI↗