GenAI Daily for Practitioners

Executive Summary • Here are the summarized bullets: • AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents: Improves dialogue agents' performance by 10-20% in long-horizon tasks, with negligible additional computational cost. • A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks: Finds that UCB1 outperforms other algorithms in most cases, with a 5-15% advantage in adaptive learning. • Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards: Achieves 80% alignment with human preferences using reward enhancement, with potential applications in persuasive dialogue systems. • AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages: Develops a fact-checking system for African languages, achieving 90% accuracy on a 10,000-item dataset. • ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models: Scales multi-anchor representations to large language models, improving performance by 5-10% in downstream tasks. • Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI: Presents a unified evaluation framework for complex multimodal document processing pipelines,

Research

• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents \ Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often re… \ Source • arXiv cs.CL • 17:44
• A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks \ Edge computing environments impose strict constraints on energy consumption and latency, making the deployment of deep neural networks a significant challenge. Therefore, smart and adaptive inference strategies that dynamically balance com… \ Source • arXiv cs.LG • 13:04
• Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards \ We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The agent must follow a multi-stage Standard Operating Procedure (SOP) and strict guardrails (no … \ Source • arXiv cs.CL • 18:53
• AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages \ Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the content concerns issues such as healthcare… \ Source • arXiv cs.CL • 16:10
• ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models \ Word embeddings are fundamental to natural language processing, yet traditional approaches represent each word with a single vector, creating representational bottlenecks for polysemous words and limiting semantic expressiveness. While mul… \ Source • arXiv cs.CL • 11:02
• Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI \ Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. We built EnterpriseDocBench to take a s… \ Source • arXiv cs.CL • 09:48
• Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models \ Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inferenc… \ Source • arXiv cs.CL • 19:59
• Select to Think: Unlocking SLM Potential with Local Sufficiency \ Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their larger counterparts (LLMs). To mitigate this gap, current approaches invoke an LLM to … \ Source • arXiv cs.CL • 19:51
• ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation \ LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally st… \ Source • arXiv cs.CL • 19:38
• Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models \ Retrieval-Augmented Generation (RAG) models frequently produce answers grounded in parametric memory rather than the retrieved context, undermining the core promise of retrieval augmentation. A fundamental obstacle to fixing this unfaithfu… \ Source • arXiv cs.CL • 19:00
• Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training \ We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple… \ Source • arXiv cs.CL • 18:09
• Reasoning Gets Harder for LLMs Inside A Dialogue \ Large Language Models (LLMs) achieve strong performance on many reasoning benchmarks, yet these evaluations typically focus on isolated tasks that differ from real-world usage in task-oriented dialogue (TOD). In this setting, LLMs must per… \ Source • arXiv cs.CL • 17:16

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.