Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models

Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise preferences, removing the need for reward modeling and policy optimization. However, recent work shows that DPO exhibits a squeezing effect, where negative gradients applied to rejected responses concentrate probability mass on high-confidence predictions while suppressing alternative responses. This phenomenon arises even in simple softmax models and can lead to systematic probability collapse during training. We introduce Gradient-Gated Preference Optimization (Gate-DPO), a method that stabilizes training by modulating rejected gradients according to the model's probability geometry. When updates target extremely low-probability responses, the gate attenuates harmful gradients while preserving standard optimization behavior. Gate-DPO addresses this optimization pathology without modifying the underlying preference objective and is complementary to existing methods such as extended SFT, IPO, and Cal-DPO. Experiments across multiple architectures and preference datasets show that Gate-DPO consistently reduces squeezing and improves chosen-response likelihood. Mass-dynamics analysis further reveals healthier optimization behavior, with improved preferred responses and reduced suppression of the overall distribution. Notably, smaller gated models can exhibit stronger chosen-response improvements than larger ungated models, suggesting that controlling gradient dynamics, rather than scale alone, is key to stable and efficient alignment.

TIJERE: A Novel Threat Intelligence Joint Extraction Model Based on Analyst Expert Knowledge

The extraction of entities and relationships from threat intelligence reports into structured formats, such as cybersecurity knowledge graphs, is essential for automated threat analysis, detection, and mitigation. However, existing joint extraction methods struggle with feature confusion, language ambiguity, noise propagation, and overlapping relations, resulting in low accuracy and poor model performance. This paper presents TIJERE, an innovative joint entity and relation extraction framework that formulates joint extraction as a multisequence labeling representation (MSLR) problem. Specifically, separate sequences are generated for each entity pair. Unlike prior tagging schemes, MSLR integrates expert domain features to enrich positional, contextual, and semantic representations of entities, thereby enhancing feature distinction and classification accuracy. Additionally, TIJERE reduces language ambiguity and enhances domain-specific generalization by leveraging SecureBERT+, a contextual language model fine-tuned on cybersecurity text. This improves both named entity recognition (NER) and relation extraction (RE). This paper also introduces DNRTI-JE, the first publicly available jointly labeled dataset for cybersecurity entity and RE, filling a crucial gap in cyber threat intelligence automation. Empirical evaluations on the curated DNRTI-JE dataset demonstrate that TIJERE achieves state-of-the-art performance, with F1-scores exceeding 0.93 for NER and 0.98 for RE, outperforming existing methods. Together, TIJERE and the standardized benchmarking DNRTI-JE dataset enable high-performance cybersecurity intelligence extraction, with transferable applications in healthcare, finance, and bioinformatics.