✍️ Text Generation

🤖 AAAI2026 · 3 paper notes

📌 Same area in other venues: 🔬 ICLR2026 (12) · 💬 ACL2026 (17) · 🧪 ICML2026 (2) · 📹 ICCV2025 (1) · 🧪 ICML2025 (1) · 💬 ACL2025 (27)

AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research

This paper proposes AutoMalDesc, an automated static analysis framework that employs an iterative self-paced learning pipeline — starting from 900 expert-annotated seed samples, fine-tuning Llama-3.3-70B via LoRA to generate pseudo-labels, applying multi-stage quality filtering to obtain 101K samples, and training a V2 model — to achieve automated malware classification and behavior description across five scripting languages, improving Batch script detection accuracy from 52.7% to 82.4%.

C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation

This paper proposes the C3TG framework, which achieves fine-grained multi-attribute controllable text generation through a two-stage approach: in the generation stage, weighted KL divergence is used to fuse attribute distributions and adjust token probabilities; in the optimization stage, an energy function (combining classifier scores and conflict penalty terms) drives iterative rewriting via a Feedback Agent. C3TG achieves 90.4% attribute accuracy across 17 attribute subcategories while substantially reducing toxicity.

Structured Language Generation Model: Loss Calibration and Formatted Decoding for Efficient Text

This paper proposes the SLGM framework, which reformulates structured prediction tasks for generative language models as classification problems via three components: structured input format, format loss, and format-aware decoding. Without introducing additional model parameters, SLGM significantly improves structural prediction performance of sub-1B models across 13 datasets spanning 5 task categories, including NER, RE, and SRL.