💬 LLMs - yfff · Scour

Representation-Guided Parameter-Efficient LLM Unlearning 🧠LLM

Guardrails in Logit Space: Safety Token Regularization for LLM Alignment 🧠LLM

Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck? 🧠LLM

Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step Sampling 🧠LLM

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models 🧠LLM

SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics 🧠LLM

Faster LLM Inference via Sequential Monte Carlo 🧠LLM

arxiv.org·5d·Hacker News

Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing 🧠LLM

Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations 🧠LLM

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models 🧠LLM

Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation 🧠LLM

Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs 🧠LLM

Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation 🧠LLM

Self-Improving Tabular Language Models via Iterative Group Alignment 🧠LLM

When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints 🧠LLM

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions 🎮Reinforcement Learning

Injecting Structured Biomedical Knowledge into Language Models: Continual Pretraining vs. GraphRAG 🧠LLM

Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications 🧠LLM

RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models 🧠LLM

Optimizing Korean-Centric LLMs via Token Pruning 🧠LLM

No more posts from yfff's subscribed feeds.

Scour all 24367 feeds Learn more about Feeds

Sign up or log in to see more results

Log in to enable infinite scrolling