arXiv:2510. 01167v2 Announce Type: replace-cross Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective.
arXiv:2607. 02781v1 Announce Type: cross Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
arXiv:2608. 16072v1 Announce Type: cross Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners.
arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.
arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.
arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.
arXiv:2511. 16992v3 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness.
arXiv:2607. 22649v1 Announce Type: new Abstract: Following complex instructions with multiple explicit constraints remains a fundamental challenge for large language models (LLMs).
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.
arXiv:2605. 04539v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness.
arXiv:2509. 25148v2 Announce Type: replace Abstract: Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback.