💬 LLMs - sworddish

Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model

📐Formal Languages Academic

arxiv.org·

Less-relevant results

Hidden Consensus:Preference-Validity Compression in Human Feedback

🧪Agent Evaluation Academic

arxiv.org·

Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison

🧪Agent Evaluation Academic

arxiv.org·

The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

🃏Imperfect Information Games Academic

arxiv.org·

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

🃏Imperfect Information Games Academic

arxiv.org·

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

🧪Agent Evaluation Academic

arxiv.org·

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

📐Formal Languages Academic

arxiv.org·

LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding

🧩Neural-Symbolic AI Academic

arxiv.org·

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

🃏Imperfect Information Games Academic

arxiv.org·

Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks

🧩Neural-Symbolic AI Academic

arxiv.org·

A Regret Minimization Framework on Preference Learning in Large Language Models

🌳Decision-Time Planning Academic

arxiv.org·

When Vision Misleads, Let Location Speak: A Worldwide Image Geo-Localization Method via Location Attention Mechanism and Large Multimodal Models

📊Prediction Markets Academic

arxiv.org·

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

🧩Neural-Symbolic AI Academic

arxiv.org·

Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning

📐Formal Languages Academic

arxiv.org·

Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair

Towards Tight Bounds for Streaming Attention

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting

A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model

Hidden Consensus:Preference-Validity Compression in Human Feedback

Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison

The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks

A Regret Minimization Framework on Preference Learning in Large Language Models

When Vision Misleads, Let Location Speak: A Worldwide Image Geo-Localization Method via Location Attention Mechanism and Large Multimodal Models

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning