Cover Image

SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Kehua, Ding, Keyan, Wang, Yuhao, Li, Menghan, Wei, Fanjunduo, Wang, Xinda, Zhang, Qiang, Chen, Huajun
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
by: Feng, Kehua, et al.
Published: (2025)

Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges
by: Tang, Yuqi, et al.
Published: (2025)

Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning
by: Zhuang, Xiang, et al.
Published: (2025)

ClinDEF: A Dynamic Evaluation Framework for Large Language Models in Clinical Reasoning
by: Tang, Yuqi, et al.
Published: (2025)

ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
by: Rao, Mingyang, et al.
Published: (2026)

Advancing biomolecular understanding and design following human instructions
by: Zhuang, Xiang, et al.
Published: (2024)

Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition
by: Feng, Kehua, et al.
Published: (2024)

Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization
by: Wang, Yuhao, et al.
Published: (2025)

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
by: Shi, Wei, et al.
Published: (2025)

SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
by: Feng, Kehua, et al.
Published: (2024)

Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions
by: Luo, Shunyang, et al.
Published: (2026)

SciCUEval: A Comprehensive Dataset for Evaluating Scientific Context Understanding in Large Language Models
by: Yu, Jing, et al.
Published: (2025)

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
by: Ding, Keyan, et al.
Published: (2025)

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
by: Li, Tianhao, et al.
Published: (2024)

Advancing LLM Safe Alignment with Safety Representation Ranking
by: Du, Tianqi, et al.
Published: (2025)

Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching
by: Li, Songze, et al.
Published: (2025)

Multilingual Safety Alignment via Self-Distillation
by: Qin, Ruiyang, et al.
Published: (2026)

Scientific Large Language Models: A Survey on Biological & Chemical Domains
by: Zhang, Qiang, et al.
Published: (2024)

A Bionic Natural Language Parser Equivalent to a Pushdown Automaton
by: Wei, Zhenghao, et al.
Published: (2024)

InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
by: Qiao, Shuofei, et al.
Published: (2026)

OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases
by: Chen, Yongrui, et al.
Published: (2025)

W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search
by: Ding, Zhenyu, et al.
Published: (2025)

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment
by: Fan, Yuchun, et al.
Published: (2025)

SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
by: Qiao, Shuofei, et al.
Published: (2026)

SaRO: Enhancing LLM Safety through Reasoning-based Alignment
by: Mou, Yutao, et al.
Published: (2025)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
by: Li, Hao, et al.
Published: (2026)

STAIR: Improving Safety Alignment with Introspective Reasoning
by: Zhang, Yichi, et al.
Published: (2025)

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
by: Deng, Qiyuan, et al.
Published: (2025)

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
by: Lou, Xinyue, et al.
Published: (2025)

Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
by: Zheng, Jiasen, et al.
Published: (2026)

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
by: In, Yeonjun, et al.
Published: (2025)

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines
by: Wang, Yuhang, et al.
Published: (2025)

Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
by: Jiang, Shuyang, et al.
Published: (2026)

RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals
by: Zhang, Xuanliang, et al.
Published: (2025)

RiOT: Efficient Prompt Refinement with Residual Optimization Tree
by: Zhou, Chenyi, et al.
Published: (2025)

VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
by: Chen, Menglan, et al.
Published: (2025)

ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models
by: Liu, Yachuan, et al.
Published: (2025)

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
by: She, Shuaijie, et al.
Published: (2024)

Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models
by: Zhang, Bowen, et al.
Published: (2024)

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
by: Wu, Di, et al.
Published: (2026)