🧠 LLMs - ghosh.debasish · Scour

LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models 📊LLM Evaluation

Language Anchoring: A Systematic Method for LLM Multilingual Adaptation ⚙️Compilers

github.com·4d·Hacker News

Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning 🧠Reasoning Models

A Survey on LLM-based Conversational User Simulation 📚RAG

LayerBoost: Layer-Aware Attention Reduction for Efficient LLMs 🧠Reasoning Models

Delineating Knowledge Boundaries for Honest Large Vision-Language Models 🧠Reasoning Models

On the Limits of Self-Improving in Large Language Models: The Singularity Is Not Near Without Symbolic Model Synthesis 🔍Mechanistic Interpretability

arxiv.org·2d·Lobsters

From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors 📦Succinct Data Structures

From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models 🧮Denotational Semantics

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities 🧠Reasoning Models

Structural Generalization on SLOG without Hand-Written Rules 🔤PLT

Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning 📊LLM Evaluation

Shared Lexical Task Representations Explain Behavioral Variability In LLMs 📊LLM Evaluation

Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence 🗄️Vector Databases

Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling 📚RAG

Extracting books from production language models 📚RAG

ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoring 📊LLM Evaluation

Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners 📊LLM Evaluation

TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models 🧠Reasoning Models

LLM-Guided Issue Generation from Uncovered Code Segments 📊LLM Evaluation

Sign up or log in to see more results

Log in to enable infinite scrolling