AI Wiki — Knowledge Base

Manaca-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge

arXiv:2610.20570v1 Announce Type: new Abstract: Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or valida

model-releasesarxiv-cs-cl

15 Oct 2026

Search: “llm”

LLM-Auction: Generative Auction towards LLM-Native Advertising

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing

P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats

LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains

LLM-OSDA: An Optimal-Stopping Dynamic Auction for Native Advertising in Multi-Turn LLM Conversations

LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation

LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface

When Does a Classifier Help an LLM? Classifier-Guided Prompting and Hybrid Classifier-LLM Models for Credit-Default Prediction

WIP: LLM Odyssey: A Game-Based Platform for Teaching LLM Engineering Concepts

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search

LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing

LLM-Rosetta: A Hub-and-Spoke Intermediate Representation for Cross-Provider LLM API Translation

Manaca-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge

Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems

Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus

LLM Agents Factory: Retrieval of Domain-Specific LLM Agents

Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control

An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models

The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models

LLM-SAA: LLM-persona Generated Distributions for Decision-making

Scheming Ability in LLM-to-LLM Strategic Interactions

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook

dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale

Offline Guidance, Online Reasoning: Reusing LLM Feedback for Small Language Models

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools

Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation

When LLM Essays Outscore Student Essays: What a Korean Writing Rubric Rewards and Where Readers Disagree

Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation

Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness

The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment

LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR

Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty

Bits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inference

From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving

M2G-LLM: Enhancing Clinical Prediction via Multimodal Graph Reasoning and LLM Context Injection

When Consistency Does Not Mean Reliability: Evaluating Local LLM Judges Against Human Ratings

Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment

LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering

T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework

Detecting LLM-Generated Tokens in Human--LLM Coauthored Text

Mitigating LLM-based p-Hacking by Preregistering for the Next LLM

ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU