AI Wiki — Knowledge Base

チームのLLM開発が本格化してきたので仲間を募集します！人数を必要以上に増やさず、一人ひとりが大きな役割を担うチームを作っています。高い基礎力と知的好奇心、そして違った強みを持つメンバーが集まって、全体の目的に向かって高い主体性を持って動いています。そんなチームの一員になれます…

チームのLLM開発が本格化してきたので仲間を募集します！人数を必要以上に増やさず、一人ひとりが大きな役割を担うチームを作っています。高い基礎力と知的好奇心、そして違った強みを持つメンバーが集まって、全体の目的に向かって高い主体性を持って動いています。そんなチームの一員になれます。僕自身もこのチームでメンバーと仕事することが何より楽しいです。 LLM経験者はもちろん歓迎。未経験でも、しばらくLL

researchdavid-ha--x

22 Aug 2026

Search: “llm”

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games

Evaluating the Efficacy of LLMs to Emulate Realistic Human Personalities

Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction

Unveiling the Depth-Performance Dilemma in Split-Federated Fine-tuning of LLMs

What AstroPT knows about galaxies, and what that can teach us about LLMs

Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron

Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

I don’t like ELI5 as default for “make this easy to understand,” a great thing about LLMs is the ability to work as universal translators ac…

Single RTX 5090: Qwen3.8-27B NVFP4 at a real 262K context in vLLM — 77 tok/s short-context, 64.7 tok/s at 128K

From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning

okay so everyone is talking about this but you guys realize it's not an LLM/foundation model or even a neural network, right???? it's probab…

Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Task

Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs

Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs

Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis

Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking

DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization

Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs

RamseyGadgets: A Graph Construction Dataset for LLMs

The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions?

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs

Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval

Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs

Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study

Do LLMs Benefit From Their Own Words?

How Robust Are LLMs to Vietnamese Dialects?

TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs

AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups

How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans

MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks

NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs

Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States

Right Answer, Wrong Heat: Explanation-Aware Evaluation and Thermal-Grounded Feedback for MLLMs on Infrared Images

Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

SymboUQ: Symbolic Uncertainty Quantification for Spatial Reasoning in LLMs

The Download: the next big thing in LLMs and how AI academic research is shifting

We built the Agentic World Cup - LLMs that compete in 1v1 Soccer. [P]

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output

Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs

GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks

Grammar Engineering Meets LLMs: Development of Cantonese and Irish ParGram Treebanks

As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture