conftrace_

← Learning Types

Deep Learning › Learning Types ›

Fine-Tuning

1,023 papers

Papers per year

1

1

1

5

25

55

64

103

118

267

312

71

Papers

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026

Select Before Use: On the Importance of Reference Model Selection in Preference Alignment ACL 2026

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion ACL 2026

Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning ACL 2026

Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge ACL 2026

TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models ACL 2026

Soft Orthogonal Low-Rank Adaptation for Knowledge Sharing in Large Language Model Continual Learning ACL 2026

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs ACL 2026

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation ACL 2026

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study ACL 2026

Instant Personalized Large Language Model Adaptation via Hypernetwork ACL 2026

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration ACL 2026

GMFL: Efficient Global Masking for Federated LLM Fine-tuning ACL 2026

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation ACL 2026

Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework ACL 2026

Localized Low-Rank Adaptation within Clustered Parameter Subspaces ACL 2026

Temporal Sampling for Forgotten Reasoning in LLMs ACL 2026

TLoRA: Task-aware Low Rank Adaptation of Large Language Models ACL 2026

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models ACL 2026

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models ACL 2026

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics ACL 2026

Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies ACL 2026

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning ACL 2026

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning ACL 2026

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients ACL 2026