nestdaddy
Web World Financial Country Tech
Showing 20 of 128 tech news articles in Research
Research
Arxiv 22 hours ago

Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure

arXiv:2608.20361v1 Announce Type: new Abstract: Automated research-idea generation systems built on large language models (LLMs) share a structural weakness: they reduce ideation to free-text recombination, random paper pairing, or embedding-similarity retrieval. The three approaches fail in the sa

Research
Arxiv 22 hours ago

Multilingual Verifier Bias in RLVR: Benchmark, Rollout Diagnosis, and the Cross-Lingual Selection Bottleneck

arXiv:2608.20362v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an answer verifier serves as a language-neutral reward function. We show that this assumption fails in multi

Research
Arxiv 22 hours ago

Hadith computational science in the age of large language models: a critical narrative review

arXiv:2608.20364v1 Announce Type: new Abstract: We examine how hadith computational science is being reshaped by transformer models, retrieval-grounded pipelines, and large language models (LLMs). Recent reviews document growth in the literature, but they do not yet provide a critical account of wh

Research
Arxiv 22 hours ago

Trilingual Topic Modeling of Sri Lankan Parliamentary Debates

arXiv:2608.20365v1 Announce Type: new Abstract: Sri Lankan parliamentary debates (Hansards) constitute a trilingual corpus of speeches in Sinhala, Tamil, and English, including code-mixed content, yet remain inaccessible to standard NLP pipelines due to layout-complex PDFs, multilingual scripts, an

Research
Arxiv 22 hours ago

Research Paper Quality Recognition Through Textual Feature Analysis

arXiv:2608.20368v1 Announce Type: new Abstract: Knowledge and innovations are shaped by using the quality and credibility of the scientific research. Yet, distinguishing between impactful, high-quality work and flawed studies remains a challenge. This paper introduces a benchmark for classifying re

Research
Arxiv 22 hours ago

ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora

arXiv:2608.20369v1 Announce Type: new Abstract: Structured reporting converts free-text radiology narratives into queryable data keys, facilitating cohort assembly, longitudinal tracking, and training label generation for medical AI. The prevailing paradigm follows a two-stage pipeline: (1) constru

Research
Arxiv 22 hours ago

When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems

arXiv:2608.20371v1 Announce Type: new Abstract: A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers for intent detection. We test this claim head-to-head and find that the honest answer is: it depends on the intent space. On full ATIS and CLINC150 we

Research
Arxiv 22 hours ago

An ambiguity taxonomy for evaluating large language model performance on clinical registry abstraction: a multi-site prospective study

arXiv:2608.20373v1 Announce Type: new Abstract: Objective: To evaluate large language model (LLM) performance on unprocessed electronic medical record (EMR) data for clinical registry abstraction. Methods: We evaluated LLM performance answering registry questions for the American College of Cardiol

Research
Arxiv 22 hours ago

VA-DPO: Valence-Arousal Direct Preference Optimization for Controllable Emotion Generation in Language Models

arXiv:2608.20374v1 Announce Type: new Abstract: How precisely can we tell a language model how to feel? Most work on emotional generation answers with a discrete label - happy, angry, sad - which cannot express a target like "mildly downcast but calm." We instead specify the desired affect as a con

Research
Arxiv 22 hours ago

GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring

arXiv:2608.20375v1 Announce Type: new Abstract: Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree builders typically construct these paths through parent-conditioned expansion, where each child token

Research
Arxiv 22 hours ago

TH-GNN: Heterogeneous Temporal Graph Neural Networks for LLM-Agent Shilling Attack Detection

arXiv:2608.20376v1 Announce Type: new Abstract: LLM agents can now generate realistic shilling profiles, fluent reviews, and coherent ratings at scale, systematically defeating recommender-system defenses. Text-only detectors that flag semantic drift in review embeddings are blind to graph structur

Research
Arxiv 22 hours ago

EditPPT: Faithful Long-Deck Slide Editing via Structured Tool-Using Multi-Agent with Dual-Modal Validators

arXiv:2608.20381v1 Announce Type: new Abstract: Automating slide editing requires simultaneously satisfying modification accuracy, preservation fidelity, and robustness to deck length. Existing LLM-based systems often fail on real-world presentation files because they rely on idealized intermediate

Research
Arxiv 22 hours ago

Decoupled Vision-Language System for Multimodal Understanding and Generation

arXiv:2608.20382v1 Announce Type: new Abstract: We introduce a new architecture design for multimodal large language models (MLLMs), Libra, capable of both multimodal understanding and generation. Libra architecture contains one vision system and one language system, connected by cross-modal bridge

Research
Arxiv 22 hours ago

Using Human-LLM Disagreement to Improve Checklist-Based Quality Appraisal

arXiv:2608.20385v1 Announce Type: new Abstract: Systematic reviews rely on quality appraisal of included studies, a process that is time-consuming and sensitive to ambiguity in checklist criteria. Although large language models (LLMs) offer opportunities to support these tasks, appraisal checklists

Research
Arxiv 22 hours ago

Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions

arXiv:2608.20387v1 Announce Type: new Abstract: While recent text-to-speech (TTS) models achieve high naturalness, controlling fine-grained expression via natural-language instructions remains challenging. We introduce Poly- InstructTTS, which learns expressive speech from open-ended instructions u

Research
Arxiv 22 hours ago

Intent Engine: Natural-Language Intent Translation for Intent-Driven Orchestration in the Compute Continuum

arXiv:2608.20388v1 Announce Type: new Abstract: Microservice placement in the compute continuum is driven by low-level Service-level Objectives (SLOs), but requiring users to specify metric-level constraints creates an adoption barrier and increases misconfiguration risk. Although large language mo

Research
Arxiv 22 hours ago

Ansari: A Retrieval-Grounded Islamic AI Assistant -- Architecture, Deployment, and Lessons from 140,000 Conversations

arXiv:2608.20390v1 Announce Type: new Abstract: General-purpose large language models (LLMs) are increasingly used to answer religious questions, but for Islamic content they carry two serious risks: factual fabrication (inventing Qur'anic verses or hadith) and subtle value misalignment. We present

Research
Arxiv 22 hours ago

ImmigrationReason: A Structured Dataset of U.S. Immigration Appeals for Legal Reasoning Research

arXiv:2608.20391v1 Announce Type: new Abstract: Most legal NLP resources draw from federal case law and focus on coarse classification, leaving administrative adjudication, where the vast majority of government decisions occur, essentially unaddressed. We introduce ImmigrationReason, a large-scale

Research
Arxiv 22 hours ago

Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants

arXiv:2608.20392v1 Announce Type: new Abstract: LLM-powered meeting assistants are deployed at scale, yet systematic evaluation of their grounding fidelity remains limited to static benchmarks that miss failure modes tied to specific discourse structures or reasoning demands. We propose Evaluation-

Research
Arxiv 22 hours ago

Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AI

arXiv:2608.20393v1 Announce Type: new Abstract: Agentic large language models (LLMs) deployed in fact-sensitive applications such as customer support must simultaneously preserve factual correctness and generate responses in a controllable stylistic register. Activation steering enables fine-tuning

Link copied to clipboard!