Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs

Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We focus on a common form of bias: when two reference concepts in the model's concept space, such as sentiment polarities (e.g., "positive" and "negative"), are asymmetrically correlated with a third, target concept, such as a reviewing aspect, the model exhibits unintended bias. For instance, the understanding of "food" should not skew toward any particular sentiment. Existing bias evaluation methods assess behavioral differences of LLMs by constructing labeled data for different social groups and measuring model responses across them, a process that requires substantial human effort and captures only a limited set of social concepts. To overcome these limitations, we propose BiasLens, a test-set-free bias analysis framework based on the structure of the model's vector space. BiasLens combines Concept Activation Vectors (CAVs) with Sparse Autoencoders (SAEs) to extract interpretable concept representations, and quantifies bias by measuring the variation in representational similarity between the target concept and each of the reference concepts. Even without labeled data, BiasLens shows strong agreement with traditional bias evaluation metrics (Spearman correlation r > 0.85). Moreover, BiasLens reveals forms of bias that are difficult to detect using existing methods. For example, in simulated clinical scenarios, a patient's insurance status can cause the LLM to produce biased diagnostic assessments. Overall, BiasLens offers a scalable, interpretable, and efficient paradigm for bias discovery, paving the way for improving fairness and transparency in LLMs.

Sentiment-Aware Recommendation Systems in E-Commerce: A Review from a Natural Language Processing Perspective

E-commerce platforms generate vast volumes of user feedback, such as star ratings, written reviews, and comments. However, most recommendation engines rely primarily on numerical scores, often overlooking the nuanced opinions embedded in free text. This paper comprehensively reviews sentiment-aware recommendation systems from a natural language processing perspective, covering advancements from 2023 to early 2025. It highlights the benefits of integrating sentiment analysis into e-commerce recommenders to enhance prediction accuracy and explainability through detailed opinion extraction. Our survey categorizes recent work into four main approaches: deep learning classifiers that combine sentiment embeddings with user item interactions, transformer based methods for nuanced feature extraction, graph neural networks that propagate sentiment signals, and conversational recommenders that adapt in real time to user feedback. We summarize model architectures and demonstrate how sentiment flows through recommendation pipelines, impacting dialogue-based suggestions. Key challenges include handling noisy or sarcastic text, dynamic user preferences, and bias mitigation. Finally, we outline research gaps and provide a roadmap for developing smarter, fairer, and more user-centric recommendation tools.

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs

Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments, and existing models have made significant progress in this area. The central challenge in MSA is multimodal fusion, which is predominantly addressed by Multimodal Transformers (MulTs). Although act as the paradigm, MulTs suffer from efficiency concerns. In this work, from the perspective of efficiency optimization, we propose and prove that MulTs are hierarchical modal-wise heterogeneous graphs (HMHGs), and we introduce the graph-structured representation pattern of MulTs. Based on this pattern, we propose an Interlaced Mask (IM) mechanism to design the Graph-Structured and Interlaced-Masked Multimodal Transformer (GsiT). It is formally equivalent to MulTs which achieves an efficient weight-sharing mechanism without information disorder through IM, enabling All-Modal-In-One fusion with only 1/3 of the parameters of pure MulTs. A Triton kernel called Decomposition is implemented to ensure avoiding additional computational overhead. Moreover, it achieves significantly higher performance than traditional MulTs. To further validate the effectiveness of GsiT itself and the HMHG concept, we integrate them into multiple state-of-the-art models and demonstrate notable performance improvements and parameter reduction on widely used MSA datasets.

Emotions in the Loop: A Survey of Affective Computing for Emotional Support

In a world where technology is increasingly embedded in our everyday experiences, systems that sense and respond to human emotions are elevating digital interaction. At the intersection of artificial intelligence and human-computer interaction, affective computing is emerging with innovative solutions where machines are humanized by enabling them to process and respond to user emotions. This survey paper explores recent research contributions in affective computing applications in the area of emotion recognition, sentiment analysis and personality assignment developed using approaches like large language models (LLMs), multimodal techniques, and personalized AI systems. We analyze the key contributions and innovative methodologies applied by the selected research papers by categorizing them into four domains: AI chatbot applications, multimodal input systems, mental health and therapy applications, and affective computing for safety applications. We then highlight the technological strengths as well as the research gaps and challenges related to these studies. Furthermore, the paper examines the datasets used in each study, highlighting how modality, scale, and diversity impact the development and performance of affective models. Finally, the survey outlines ethical considerations and proposes future directions to develop applications that are more safe, empathetic and practical.

OODTE: A Differential Testing Engine for the ONNX Optimizer

With $700$ stars on GitHub and part of the official ONNX repository, the ONNX Optimizer consists of the standard method to apply graph-based optimizations on ONNX models. However, its ability to preserve model accuracy across optimizations, has not been rigorously explored. We propose OODTE, a utility to automatically and thoroughly assess the correctness of the ONNX Optimizer. OODTE follows a simple, yet effective differential testing and evaluation approach that can be easily adopted to other compiler optimizers. In particular, OODTE utilizes a number of ONNX models, then optimizes them and executes both the original and the optimized variants across a user-defined set of inputs, while automatically logging any issues with the optimization process. Finally, for successfully optimized models, OODTE compares the results, and, if any accuracy deviations are observed, it iteratively repeats the process for each pass of the ONNX Optimizer, to localize the root cause of the differences observed. Using OODTE, we sourced well-known $130$ models from the official ONNX Model Hub, used for a wide variety of tasks (classification, object detection, semantic segmentation, text summarization, question and answering, sentiment analysis) from the official ONNX model hub. We detected 15 issues, 14 of which were previously unknown, associated with optimizer crashes and accuracy deviations. We also observed $9.2$% of all model instances presenting issues leading into the crash of the optimizer, or the generation of an invalid model while using the primary optimizer strategies. In addition, $30$% of the classification models presented accuracy differences across the original and the optimized model variants, while $16.6$% of semantic segmentation and object detection models are also affected, at least to a limited extent.

Automated Sentiment Classification and Topic Discovery in Large-Scale Social Media Streams

We present a framework for large-scale sentiment and topic analysis of Twitter discourse. Our pipeline begins with targeted data collection using conflict-specific keywords, followed by automated sentiment labeling via multiple pre-trained models to improve annotation robustness. We examine the relationship between sentiment and contextual features such as timestamp, geolocation, and lexical content. To identify latent themes, we apply Latent Dirichlet Allocation (LDA) on partitioned subsets grouped by sentiment and metadata attributes. Finally, we develop an interactive visualization interface to support exploration of sentiment trends and topic distributions across time and regions. This work contributes a scalable methodology for social media analysis in dynamic geopolitical contexts.

Bug Destiny Prediction in Large Open-Source Software Repositories through Sentiment Analysis and BERT Topic Modeling

This study explores a novel approach to predicting key bug-related outcomes, including the time to resolution, time to fix, and ultimate status of a bug, using data from the Bugzilla Eclipse Project. Specifically, we leverage features available before a bug is resolved to enhance predictive accuracy. Our methodology incorporates sentiment analysis to derive both an emotionality score and a sentiment classification (positive or negative). Additionally, we integrate the bug's priority level and its topic, extracted using a BERTopic model, as features for a Convolutional Neural Network (CNN) and a Multilayer Perceptron (MLP). Our findings indicate that the combination of BERTopic and sentiment analysis can improve certain model performance metrics. Furthermore, we observe that balancing model inputs enhances practical applicability, albeit at the cost of a significant reduction in accuracy in most cases. To address our primary objectives, predicting time-to-resolution, time-to-fix, and bug destiny, we employ both binary classification and exact time value predictions, allowing for a comparative evaluation of their predictive effectiveness. Results demonstrate that sentiment analysis serves as a valuable predictor of a bug's eventual outcome, particularly in determining whether it will be fixed. However, its utility is less pronounced when classifying bugs into more complex or unconventional outcome categories.

A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification

With the advance of large language models (LLMs), LLMs have been utilized for the various tasks. However, the issues of variability and reproducibility of results from each trial of LLMs have been largely overlooked in existing literature while actual human annotation uses majority voting to resolve disagreements among annotators. Therefore, this study introduces the straightforward ensemble strategy to a sentiment analysis using LLMs. As the results, we demonstrate that the ensemble of multiple inference using medium-sized LLMs produces more robust and accurate results than using a large model with a single attempt with reducing RMSE by 18.6%.

Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks

Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training process. In this study, we examine how different response format: binary versus continuous, may systematically influence LLMs' judgments. In a value statement judgments task and a text sentiment analysis task, we prompted LLMs to simulate human responses and tested both formats across several models, including both open-source and commercial models. Our findings revealed a consistent negative bias: LLMs were more likely to deliver "negative" judgments in binary formats compared to continuous ones. Control experiments further revealed that this pattern holds across both tasks. Our results highlight the importance of considering response format when applying LLMs to decision tasks, as small changes in task design can introduce systematic biases.

Linguistic Complexity and Socio-cultural Patterns in Hip-Hop Lyrics

This paper presents a comprehensive computational framework for analyzing linguistic complexity and socio-cultural trends in hip-hop lyrics. Using a dataset of 3,814 songs from 146 influential artists spanning four decades (1980-2020), we employ natural language processing techniques to quantify multiple dimensions of lyrical complexity. Our analysis reveals a 23.7% increase in vocabulary diversity over the study period, with East Coast artists demonstrating 17.3% higher lexical variation than other regions. Rhyme density increased by 34.2% across all regions, with Midwest artists exhibiting the highest technical complexity (3.04 rhymes per line). Topic modeling identified significant shifts in thematic content, with social justice themes decreasing from 28.5% to 13.8% of content while introspective themes increased from 7.6% to 26.3%. Sentiment analysis demon- strated that lyrics became significantly more negative during sociopolitical crises, with polarity decreasing by 0.31 following major social unrest. Multi-dimensional analysis revealed four dis- tinct stylistic approaches that correlate strongly with geographic origin (r=0.68, p!0.001) and time period (r=0.59, p<0.001). These findings establish quantitative evidence for the evolution of hip- hop as both an art form and a reflection of societal dynamics, providing insights into the interplay between linguistic innovation and cultural context in popular music.