Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness

Prior work on fairness in large language models (LLMs) has primarily focused on access-level behaviors such as refusals and safety filtering. However, equitable access does not ensure equitable interaction quality once a response is provided. In this paper, we conduct a controlled fairness audit examining how LLMs differ in tone, uncertainty, and linguistic framing across demographic identities after access is granted. Using a counterfactual prompt design, we evaluate GPT-4 and LLaMA-3.1-70B on career advice tasks while varying identity attributes along age, gender, and nationality. We assess access fairness through refusal analysis and measure interaction quality using automated linguistic metrics, including sentiment, politeness, and hedging. Identity-conditioned differences are evaluated using paired statistical tests. Both models exhibit zero refusal rates across all identities, indicating uniform access. Nevertheless, we observe systematic, model-specific disparities in interaction quality: GPT-4 expresses significantly higher hedging toward younger male users, while LLaMA exhibits broader sentiment variation across identity groups. These results show that fairness disparities can persist at the interaction level even when access is equal, motivating evaluation beyond refusal-based audits.

Large Language Model and Formal Concept Analysis: a comparative study for Topic Modeling

Topic modeling is a research field finding increasing applications: historically from document retrieving, to sentiment analysis and text summarization. Large Language Models (LLM) are currently a major trend in text processing, but few works study their usefulness for this task. Formal Concept Analysis (FCA) has recently been presented as a candidate for topic modeling, but no real applied case study has been conducted. In this work, we compare LLM and FCA to better understand their strengths and weakneses in the topic modeling field. FCA is evaluated through the CREA pipeline used in past experiments on topic modeling and visualization, whereas GPT-5 is used for the LLM. A strategy based on three prompts is applied with GPT-5 in a zero-shot setup: topic generation from document batches, merging of batch results into final topics, and topic labeling. A first experiment reuses the teaching materials previously used to evaluate CREA, while a second experiment analyzes 40 research articles in information systems to compare the extracted topics with the underling subfields.

SentiFuse: Deep Multi-model Fusion Framework for Robust Sentiment Extraction

Sentiment analysis models exhibit complementary strengths, yet existing approaches lack a unified framework for effective integration. We present SentiFuse, a flexible and model-agnostic framework that integrates heterogeneous sentiment models through a standardization layer and multiple fusion strategies. Our approach supports decision-level fusion, feature-level fusion, and adaptive fusion, enabling systematic combination of diverse models. We conduct experiments on three large-scale social-media datasets: Crowdflower, GoEmotions, and Sentiment140. These experiments show that SentiFuse consistently outperforms individual models and naive ensembles. Feature-level fusion achieves the strongest overall effectiveness, yielding up to 4\% absolute improvement in F1 score over the best individual model and simple averaging, while adaptive fusion enhances robustness on challenging cases such as negation, mixed emotions, and complex sentiment expressions. These results demonstrate that systematically leveraging model complementarity yields more accurate and reliable sentiment analysis across diverse datasets and text types.

Leveraging Textual-Cues for Enhancing Multimodal Sentiment Analysis by Object Recognition

Multimodal sentiment analysis, which includes both image and text data, presents several challenges due to the dissimilarities in the modalities of text and image, the ambiguity of sentiment, and the complexities of contextual meaning. In this work, we experiment with finding the sentiments of image and text data, individually and in combination, on two datasets. Part of the approach introduces the novel `Textual-Cues for Enhancing Multimodal Sentiment Analysis' (TEMSA) based on object recognition methods to address the difficulties in multimodal sentiment analysis. Specifically, we extract the names of all objects detected in an image and combine them with associated text; we call this combination of text and image data TEMS. Our results demonstrate that only TEMS improves the results when considering all the object names for the overall sentiment of multimodal data compared to individual analysis. This research contributes to advancing multimodal sentiment analysis and offers insights into the efficacy of TEMSA in combining image and text data for multimodal sentiment analysis.

DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis

Aspect-Based Sentiment Analysis (ABSA) focuses on extracting sentiment at a fine-grained aspect level and has been widely applied across real-world domains. However, existing ABSA research relies on coarse-grained categorical labels (e.g., positive, negative), which limits its ability to capture nuanced affective states. To address this limitation, we adopt a dimensional approach that represents sentiment with continuous valence-arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. To this end, we introduce DimABSA, the first multilingual, dimensional ABSA resource annotated with both traditional ABSA elements (aspect terms, aspect categories, and opinion terms) and newly introduced VA scores. This resource contains 76,958 aspect instances across 42,590 sentences, spanning six languages and four domains. We further introduce three subtasks that combine VA scores with different ABSA elements, providing a bridge from traditional ABSA to dimensional ABSA. Given that these subtasks involve both categorical and continuous outputs, we propose a new unified metric, continuous F1 (cF1), which incorporates VA prediction error into standard F1. We provide a comprehensive benchmark using both prompted and fine-tuned large language models across all subtasks. Our results show that DimABSA is a challenging benchmark and provides a foundation for advancing multilingual dimensional ABSA.

StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing

Live streaming platforms require real-time monitoring and reaction to social signals, utilizing partial and asynchronous evidence from video, text, and audio. We propose StreamSense, a streaming detector that couples a lightweight streaming encoder with selective routing to a Vision-Language Model (VLM) expert. StreamSense handles most timestamps with the lightweight streaming encoder, escalates hard/ambiguous cases to the VLM, and defers decisions when context is insufficient. The encoder is trained using (i) a cross-modal contrastive term to align visual/audio cues with textual signals, and (ii) an IoU-weighted loss that down-weights poorly overlapping target segments, mitigating label interference across segment boundaries. We evaluate StreamSense on multiple social streaming detection tasks (e.g., sentiment classification and hate content moderation), and the results show that StreamSense achieves higher accuracy than VLM-only streaming while only occasionally invoking the VLM, thereby reducing average latency and compute. Our results indicate that selective escalation and deferral are effective primitives for understanding streaming social tasks. Code is publicly available on GitHub.

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models

Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level guidance procedures or trajectory optimization mechanisms. In this work, we introduce Iterative Latent Representation Refinement (ILRR), a learning-free framework for steering DLMs using a single reference sequence. ILRR guides generation by dynamically aligning the internal activations of the generated sequence with those of a given reference throughout the denoising process. This approach captures and transfers high-level semantic properties, with a tunable steering scale enabling flexible control over attributes such as sentiment. We further introduce Spatially Modulated Steering, an extension that enables steering long texts using shorter references by regulating guidance intensity across the sequence. Empirically, we demonstrate that ILRR achieves effective attribute steering on LLaDA and MDLM architectures with a minor computational overhead, requiring only one additional parallel forward pass per denoising step. Under the same compute budget, ILRR improves attribute accuracy over comparable baselines by 10$\%$ to 60$\%$ points, while maintaining high generation quality.

Beyond Forgetting: Machine Unlearning Elicits Controllable Side Behaviors and Capabilities

We consider representation misdirection (RM), a class of LLM unlearning methods that achieves forgetting by manipulating the forget-representations, that is, latent representations of forget samples. Despite being important, the roles of target vectors used in RM, however, remain underexplored. Here, we approach and revisit RM through the lens of the linear representation hypothesis. Specifically, if one can somehow identify a one-dimensional representation corresponding to a high-level concept, the linear representation hypothesis enables linear operations on this concept vector within the forget-representation space. Under this view, we hypothesize that, beyond forgetting, machine unlearning elicits controllable side behaviors and stronger side capabilities corresponding to the high-level concept. Our hypothesis is empirically validated across a wide range of tasks, including behavioral control (e.g., controlling unlearned models' truth, sentiment, and refusal) and capability enhancement (e.g., improving unlearned models' in-context learning capability). Our findings reveal that this fairly attractive phenomenon could be either a hidden risk if misused or a mechanism that can be harnessed for developing models that require stronger capabilities and controllable behaviors.

More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests

Large Language Model (LLM) Agents are advancing quickly, with the increasing leveraging of LLM Agents to assist in development tasks such as code generation. While LLM Agents accelerate code generation, studies indicate they may introduce adverse effects on development. However, existing metrics solely measure pass rates, failing to reflect impacts on long-term maintainability and readability, and failing to capture human intuitive evaluations of PR. To increase the comprehensiveness of this problem, we investigate and evaluate the characteristics of LLM to know the pull requests' characteristics beyond the pass rate. We observe the code quality and maintainability within PRs based on code metrics to evaluate objective characteristics and developers' reactions to the pull requests from both humans and LLM's generation. Evaluation results indicate that LLM Agents frequently disregard code reuse opportunities, resulting in higher levels of redundancy compared to human developers. In contrast to the quality issues, our emotions analysis reveals that reviewers tend to express more neutral or positive emotions towards AI-generated contributions than human ones. This disconnect suggests that the surface-level plausibility of AI code masks redundancy, leading to the silent accumulation of technical debt in real-world development environments. Our research provides insights for improving human-AI collaboration.

Opinion Consensus Formation Among Networked Large Language Models

Can classical consensus models predict the group behavior of large language models (LLMs)? We examine multi-round interactions among LLM agents through the DeGroot framework, where agents exchange text-based messages over diverse communication graphs. To track opinion evolution, we map each message to an opinion score via sentiment analysis. We find that agents typically reach consensus and the disagreement between the agents decays exponentially. However, the limiting opinion departs from DeGroot's network-centrality-weighted forecast. The consensus between LLM agents turns out to be largely insensitive to initial conditions and instead depends strongly on the discussion subject and inherent biases. Nevertheless, transient dynamics align with classical graph theory and the convergence rate of opinions is closely related to the second-largest eigenvalue of the graph's combination matrix. Together, these findings can be useful for LLM-driven social-network simulations and the design of resource-efficient multi-agent LLM applications.