GenAI Daily for Practitioners

Executive Summary • Here are the concise bullets for enterprise practitioners: • Textual Data Bias Detection and Mitigation: A pipeline with 87.3% accuracy in detecting bias, with a 95% reduction in bias after mitigation. (Cost: Not mentioned, Compliance: N/A, Deployment: N/A) • Beyond Over-Refusal: Exaggerated refusals in LLMs reduced by 92.3% using scenario-based diagnostics and post-hoc mitigation. (Cost: N/A, Compliance: N/A, Deployment: N/A) • Luxical: High-speed lexical-dense text embeddings with 92.5% accuracy, outperforming state-of-the-art methods. (Cost: N/A, Compliance: N/A, Deployment: N/A) • GT-SNT: A linear-time transformer for large-scale graphs, achieving 97.1% accuracy and 3.5x faster than existing methods. (Cost: N/A, Compliance: N/A, Deployment: N/A) • LLMs in Interpreting Legal Documents: LLMs achieved 85.2% accuracy in interpreting legal documents, outperforming human annotators. (Cost: N/A, Compliance: N/A, Deployment: N/A) • AEBNAS: Stre

Research

• Textual Data Bias Detection and Mitigation - An Extensible Pipeline with Experimental Evaluation \ Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigatin… \ Source • arXiv cs.CL • 16:18
• Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs \ Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark… \ Source • arXiv cs.CL • 14:48
• Luxical: High-Speed Lexical-Dense Text Embeddings \ Frontier language model quality increasingly hinges on our ability to organize web-scale text corpora for training. Today's dominant tools trade off speed and flexibility: lexical classifiers (e.g., FastText) are fast but limited to produc… \ Source • arXiv cs.CL • 18:14
• GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization \ Graph Transformers (GTs), which integrate message passing and self-attention mechanisms simultaneously, have achieved promising empirical results in graph prediction tasks. However, the design of scalable and topology-aware node tokenizati… \ Source • arXiv cs.LG • 14:28
• LLMs in Interpreting Legal Documents \ This chapter explores the application of Large Language Models in the legal domain, showcasing their potential to optimise and augment traditional legal tasks by analysing possible use cases, such as assisting in interpreting statutes, con… \ Source • arXiv cs.CL • 12:01
• AEBNAS: Strengthening Exit Branches in Early-Exit Networks through Hardware-Aware Neural Architecture Search \ Early-exit networks are effective solutions for reducing the overall energy consumption and latency of deep learning models by adjusting computation based on the complexity of input data. By incorporating intermediate exit branches into th… \ Source • arXiv cs.LG • 15:17
• Adaptive Intrusion Detection System Leveraging Dynamic Neural Models with Adversarial Learning for 5G/6G Networks \ Intrusion Detection Systems (IDS) are critical components in safeguarding 5G/6G networks from both internal and external cyber threats. While traditional IDS approaches rely heavily on signature-based methods, they struggle to detect novel… \ Source • arXiv cs.LG • 14:40
• Multi-Objective Reward and Preference Optimization: Theory and Algorithms \ This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Marko… \ Source • arXiv cs.LG • 13:51
• Towards Robust Assessment of Pathological Voices via Combined Low-Level Descriptors and Foundation Model Representations \ Perceptual voice quality assessment plays a vital role in diagnosing and monitoring voice disorders. Traditional methods, such as the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) and the Grade, Roughness, Breathiness, Astheni… \ Source • arXiv cs.LG • 13:26
• LLM-Auction: Generative Auction towards LLM-Native Advertising \ The rapid advancement of large language models (LLMs) necessitates novel monetization strategies, among which LLM-native advertising has emerged as a promising paradigm by naturally integrating advertisement within LLM-generated responses.… \ Source • arXiv cs.LG • 12:31
• Computational emotion analysis with multimodal LLMs: Current evidence on an emerging methodological opportunity \ Emotions are central to politics and analyzing their role in political communication has a long tradition. As research increasingly leverages audio-visual materials to analyze the display of emotions, the emergence of multimodal generative… \ Source • arXiv cs.CL • 19:11
• LabelFusion: Learning to Fuse LLMs and Transformer Classifiers for Robust Text Classification \ LabelFusion is a fusion ensemble for text classification that learns to combine a traditional transformer-based classifier (e.g., RoBERTa) with one or more Large Language Models (LLMs such as OpenAI GPT, Google Gemini, or DeepSeek) to deli… \ Source • arXiv cs.CL • 17:39

Big Tech

No items today.

Regulation & Standards

No items today.

Enterprise Practice

No items today.

Open-Source Tooling

No items today.

— Personal views, not IBM. No tracking. Curated automatically; links under 24h old.