Entities · Models
Llama~3.1 8B
45 articles tagged with this entity.
-
Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design
-
A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements
-
Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
-
AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations
-
Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism
-
A Mechanistic View of Authority Hierarchy in LLM Sycophancy
-
Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
-
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference
-
Small edits, large models: How Wikipedia advocacy shapes LLM values
-
AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
-
Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks
-
Unintended Effects of Geographic Conditioning in Large Language Models
-
MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition
-
PolyKV: Heterogeneous Retention and Allocation for KV Cache Compression
-
Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning
-
Small LLMs: Pruning vs. Training from Scratch
-
How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions
-
Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects
-
TSAQA: Time Series Analysis Question And Answering Benchmark
-
Synthetic Contrastive Reasoning for Multi-Table Q&A
-
GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection
-
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
-
TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization
-
Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol
-
T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
-
Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware
-
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
-
TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
-
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference
-
MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
-
Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
-
Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement
-
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
-
PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models
-
What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
-
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
-
RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian
-
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
-
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
-
The Realignment Problem: When Right becomes Wrong in LLMs
-
Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
-
How Language Models Process Negation
-
CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features