Large Language Model

Large language models (LLMs) are sophisticated AI systems designed to process and generate human-like text, aiming to improve various natural language processing tasks. Current research focuses on enhancing LLM safety, efficiency (through techniques like quantization and optimized decoding), and fairness, as well as improving their ability to perform complex reasoning and handle diverse instructions. These advancements are significant because they address critical limitations in current LLMs and pave the way for broader applications across diverse fields, including healthcare, legal tech, and autonomous systems.

7659papers

Papers - Page 33

March 25, 2025

RL-finetuning LLMs from on- and off-policy data with a single algorithm
Baseline Algorithm Policy Gradient Consistent Generation Policy Data Reward Maximization Practical Algorithm Medical LLM Large Language Model
HoarePrompt: Structural Reasoning About Program Correctness in Natural Language
Program Analysis Visual Naturalness Natural Language Human Language Correctness Check Large Language Model Structured Reasoning
Context-Efficient Retrieval with Factual Decomposition
Large Language Model Inference Efficiency Large Corpus Context Retrieval App to App Retrieval Episodic Memory
Scaling Laws of Synthetic Data for Language Models
Scaling Law Large Language Model Language Model Synthetic Data Synthetic Datasets Synthetic Data Generation
KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models
Natural Language Processing Large Language Model Model Hallucination Data Detection Data Driven Approach Generative Model Language Generation
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Positive Reinforcement Reinforcement Learning Reason Giving DH Research Complex Reasoning LeArning Abstract Large Language Model
ImF: Implicit Fingerprint for Large Language Models
Fingerprint Recognition Latent Fingerprint Adversarial Scenario Large Language Model Partial Fingerprint Country Recognition
Membership Inference Attacks on Large-Scale Models: A Survey
Large Scale Model Inference Attack Large Multimodal Model Membership Inference Attack Timely Survey Privacy Threat Large Language Model
MARS: Memory-Enhanced Agents with Reflective Self-improvement
Natural Language Processing Long Term Memory New Framework Agent Smith Large Language Model Self Improvement
Linguistic Blind Spots of Large Language Models
Linguistic Analysis Semantic Understanding Large Language Model Natural Language Question
VisualQuest: A Diverse Image Dataset for Evaluating Visual Recognition in LLMs
Recognition Task Multimodal Reasoning Large Language Model Visual Recognition Multimodal Large Language Model Image Datasets

March 24, 2025

LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages
Large Language Model Code Quality Tuned Llama Model AI Driven Automation LLM Benchmark Programming Language Scientific Workflow Real World Code
A Survey of Large Language Model Agents for Question Answering
Large Language Model Question Answering Timely Survey Answer Generation
Overtrained Language Models Are Harder to Fine-Tune
Fine Tuning Pre Training Large Language Model Pretrained Language Model Pre Trained
Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education
Resume Job Implicit Bias Gender Inclusive Text Task Alignment Evaluating Bias Large Language Model
Language Model Uncertainty Quantification with Attention Chain
Uncertainty Quantification Reasoning Benchmark Language Model Large Language Model
Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
LLM Fine Tuning Large Language Model Large Language Full Model Task Specific
Understanding and Improving Information Preservation in Prompt Compression for LLMs
Linear Compression Prompt Compression Large Language Model Human Understanding Compression Technique Knowledge Intensive Task Content Preservation Style PROMPT
Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation
Large Language Model Absolute Stance Bias Expert Tax Judge LLM a a Judge First Stage Ranker Retrieval Performance Research Assistant
ELM: Ensemble of Language Models for Predicting Tumor Group from Pathology Reports
Language Model Diverse Ensemble Pathology Data Real Tumor Cancer Classification Large Language Model

Large Language Model

Papers - Page 33

RL-finetuning LLMs from on- and off-policy data with a single algorithm

HoarePrompt: Structural Reasoning About Program Correctness in Natural Language

Context-Efficient Retrieval with Factual Decomposition

Scaling Laws of Synthetic Data for Language Models

KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

ImF: Implicit Fingerprint for Large Language Models

Membership Inference Attacks on Large-Scale Models: A Survey

MARS: Memory-Enhanced Agents with Reflective Self-improvement

Linguistic Blind Spots of Large Language Models

VisualQuest: A Diverse Image Dataset for Evaluating Visual Recognition in LLMs

LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages

A Survey of Large Language Model Agents for Question Answering

Overtrained Language Models Are Harder to Fine-Tune

Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education

Language Model Uncertainty Quantification with Attention Chain

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Understanding and Improving Information Preservation in Prompt Compression for LLMs

Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation

ELM: Ensemble of Language Models for Predicting Tumor Group from Pathology Reports