Tag: Alignment

All the articles with the tag "Alignment".

• Belief Injection for Epistemic Control in Linguistic State Space

  Published: 16 May, 2025 |  at  11:37 AM

  

  96.91 🤔

  This paper proposes belief injection as a proactive epistemic control mechanism to shape AI agents' internal linguistic belief states within the Semantic Manifold framework, offering diverse strategies for guiding reasoning and alignment, though it lacks empirical validation.

• Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs

  Published: 8 May, 2025 |  at  11:07 AM

  

  94.57 🤔

  This paper proposes a three-dimensional taxonomy and develops TTP and HarmFormer tools to filter harmful content from web-scale LLM pretraining datasets, revealing significant toxicity prevalence and persistent safety gaps through benchmarks like HAVOC.

• Reward Reasoning Model

  Published: 24 May, 2025 |  at  11:08 AM

  

  92.11 🤔

  本文提出奖励推理模型（RRMs），通过链式推理过程在生成奖励前自适应利用测试时计算资源，在多个奖励建模基准和实际应用中显著提升性能，尤其在复杂推理任务上表现优异。

• Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

  Published: 20 May, 2025 |  at  11:09 AM

  

  90.43 🤔

  本文通过系统性实验证明，纯强化学习（RL）训练不仅提升大型语言模型的复杂推理能力，还能隐式培养过程奖励模型（PRM）能力，提出Self-PRM框架以进一步改进性能，但也揭示了其在高难度问题上的低精度局限。

• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling

  Published: 26 May, 2025 |  at  11:41 AM

  

  87.45 🤔

  本文提出响应条件Bradley-Terry（Rc-BT）模型，通过区分语义意图和长度指令，显著缓解大语言模型在RLHF中的长度偏见，并提升长度指令遵循能力，实验验证了其在多个模型和数据集上的优越性。