GenAI Daily for Practitioners

Executive Summary • Here are the concise, non-sensationalist bullets for enterprise practitioners: • RexBERT: Context Specialized Bidirectional Encoders for E-commerce: • + Achieves 2.5% improvement in e-commerce search relevance over baseline. • + Trained on 1.4M product descriptions and 10M search queries. • + No additional computational resources required. • Trust The Typical: • + Introduces a novel approach to detect unusual text patterns in online data.

Research

• RexBERT: Context Specialized Bidirectional Encoders for E-commerce \ Encoder-only transformers remain indispensable in retrieval, classification, and ranking systems where latency, stability, and cost are paramount. Most general purpose encoders, however, are trained on generic corpora with limited coverage… \ Source • arXiv cs.CL • 15:32
• Trust The Typical \ Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from… \ Source • arXiv cs.CL • 15:06
• LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding \ The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this… \ Source • arXiv cs.CL • 14:34
• LinGO: A Linguistic Graph Optimization Framework with LLMs for Interpreting Intents of Online Uncivil Discourse \ Detecting uncivil language is crucial for maintaining safe, inclusive, and democratic online spaces. Yet existing classifiers often misinterpret posts containing uncivil cues but expressing civil intents, leading to inflated estimates of h… \ Source • arXiv cs.CL • 16:56
• Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection \ Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies that either fail to c… \ Source • arXiv cs.CL • 14:25
• $C$-$ΔΘ$: Circuit-Restricted Weight Arithmetic for Selective Refusal \ Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity. Activation steering is widely used, but it requires runtime… \ Source • arXiv cs.CL • 14:10
• CreditAudit: 2$^\text{nd}$ Dimension for LLM Evaluation and Selection \ Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only marginal differences. However, these scores often fail to match users' day to day experience, becaus… \ Source • arXiv cs.CL • 12:10
• ROSA-Tuning: Enhancing Long-Context Modeling via Suffix Matching \ Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce computational complexity, but they typically suffer from a limited cove… \ Source • arXiv cs.CL • 11:02
• SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents \ LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression approaches such as Long… \ Source • arXiv cs.CL • 10:20
• Verification and Identification in ECG biometric on large-scale \ This work studies electrocardiogram (ECG) biometrics at large scale, directly addressing a critical gap in the literature: the scarcity of large-scale evaluations with operational metrics and protocols that enable meaningful standardizatio… \ Source • arXiv cs.LG • 18:47
• MTS-JEPA: Multi-Resolution Joint-Embedding Predictive Architecture for Time-Series Anomaly Prediction \ Multivariate time series underpin modern critical infrastructure, making the prediction of anomalies a vital necessity for proactive risk mitigation. While Joint-Embedding Predictive Architectures (JEPA) offer a promising framework for mod… \ Source • arXiv cs.LG • 16:11
• Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models \ Drawing on constructs from psychology, prior work has identified a distinction between explicit and implicit bias in large language models (LLMs). While many LLMs undergo post-training alignment and safety procedures to avoid expressions o… \ Source • arXiv cs.CL • 17:44

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.