GPRL carries a k-dimensional skew-symmetric preference structure into policy updates with per-dimension advantages and a drift monitor, yielding 56.51% length-controlled win rate on AlpacaEval 2.0 from Llama-3-8B-Instruct while outperforming SimPO and SPPO on other benchmarks.
Alphadpo: Adaptive reward margin for direct preference optimization
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall improvement in simultaneous alignment.
LocalAlign generates near-target adversarial examples via prompting and applies margin-aware alignment training to enforce tighter boundaries against prompt injection attacks.
DPOP augments DPO with a conditional penalty on reference-greedy responses and reports 5.3% and 4.4% relative win-rate gains on AlpacaEval 2.0 for two models.
PEPO is a single-step pessimistic ensemble algorithm for direct preference optimization that provably avoids over-optimization by depending only on single-policy concentrability without knowing the data distribution or learning an explicit reward model.
citing papers explorer
-
General Preference Reinforcement Learning
GPRL carries a k-dimensional skew-symmetric preference structure into policy updates with per-dimension advantages and a drift monitor, yielding 56.51% length-controlled win rate on AlpacaEval 2.0 from Llama-3-8B-Instruct while outperforming SimPO and SPPO on other benchmarks.
-
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall improvement in simultaneous alignment.
-
LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
LocalAlign generates near-target adversarial examples via prompting and applies margin-aware alignment training to enforce tighter boundaries against prompt injection attacks.
-
Boosting Direct Preference Optimization with Penalization
DPOP augments DPO with a conditional penalty on reference-greedy responses and reports 5.3% and 4.4% relative win-rate gains on AlpacaEval 2.0 for two models.
-
Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution
PEPO is a single-step pessimistic ensemble algorithm for direct preference optimization that provably avoids over-optimization by depending only on single-policy concentrability without knowing the data distribution or learning an explicit reward model.