Key papers

• When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models (2026)
  Sai Kartheek Reddy Kasu et al.
  5.82
• K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling (2026)
  Zhiwei Tang et al.
  5.82
• Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study (2026)
  Dezhi Yu et al.
  4.95
• Black-Box Inference of LLM Architectural Properties with Restrictive API Access (2026)
  Christopher Ellis et al.
  4.39
• PreAct-Bench: Benchmarking Predictive Monitoring in LLMs (2026)
  Hainiu Xu et al.
  4.33
• A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations (2026)
  Sophie Zhao
  4.33
• RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference (2026)
  Anirudh Sekar
  4.33
• Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation (2026)
  Jakub Mas{\l}owski et al.
  4.33
• Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory (2026)
  Suozhao Ji et al.
  4.33
• Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports (2026)
  Olga Shakhmatova et al.
  4.33
• Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs (2026)
  Weijia Zhang et al.
  4.33
• Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows (2026)
  Shikun Liu et al.
  4.33
• Statistical Impossibility And Possibility Of Aligning Llms With Human Preferences: From Condorcet Paradox To Nash Equilibrium (2026)
  Kaizhao Liu, Qi Long, Zhekun Shi, et al.
  4.20
• A Systematic Evaluation of Traditional Privacy Policy Analysis Tools Against LLMs (2026)
  Madhav Aryal et al.
  3.51
• EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning (2026)
  Guhong Chen et al.
  3.45
• Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal (2026)
  Leon Bergen et al.
  3.45
• Small LLMs: Pruning vs. Training from Scratch (2026)
  Yufeng Xu et al.
  3.45
• JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety (2026)
  Yuan Xiong et al.
  2.00
• Adaptive Multi-subspace Representation Steering For Attribute Alignment In Large Language Models (2026)
  Xinyan Jiang, Lin Zhang, Jiayi Zhang, et al.
  1.94
• STAR: Detecting Inference-time Backdoors In LLM Reasoning Via State-transition Amplification Ratio (2026)
  Seong-Gyu Park, Sohee Park, Jisu Lee, et al.
  1.94
• PRISM: Probing Reasoning, Instruction, And Source Memory In LLM Hallucinations (2026)
  Yuhe Wu, Guangyu Wang, Yuran Chen, et al.
  1.94
• Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens (2025)
  Salahuddin Salahuddin et al.
  1.33
• Defending Against Alignment-breaking Attacks Via Robustly Aligned LLM (2023)
  Bochuan Cao, Yuanpu Cao, Lu Lin, et al.
  0.00
• Is Poisoning A Real Threat To LLM Alignment? Maybe More So Than You Think (2024)
  Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, et al.
  0.00
• Round Trip Translation Defence Against Large Language Model Jailbreaking Attacks (2024)
  Canaan Yung, Hadi Mohaghegh Dolatabadi, Sarah Erfani, et al.
  0.00