The paper reproduces five factuality alignment methods for large language models—three on‑policy RL approaches (PPO, GRPO, Dr.GRPO) and two offline preference optimization methods (DPO, KTO)—using a common benchmark and evaluation metrics. None of the methods consistently outperforms the base model, and the rewards appear to favor format, length, or brevity rather than factuality or relevance. The study also highlights problems with current evaluation practices, noting that metrics and benchmarks often fail to measure prompt relevance and rely on fragile LLM judges and retrieval for verification.
arXiv:2610.18415v1 Announce Type: cross Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment st...
PADM'E is a method for synthesizing preference‑aligned data to meta‑evaluate language‑model (LM) evaluators of agentic behaviors. It reframes meta‑evaluation as a preference judgment problem, generating criterion‑based data with small LMs and no human involvement. In a prototype, PADM'E produced 1,000 samples across four domains and three criteria, and human validation showed agreement with human judgment rising from 73% to 85% compared to a naive baseline.
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:2609.06893v1 Announce Type: cross Abstract: Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational eff...
arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.
The paper introduces Comparison-based Preference Optimization (ComPO), a zeroth-order method that aligns large language models with human preferences using comparison oracles instead of direct differentiable loss optimization. It provides theoretical convergence guarantees for both offline and online variants under smoothness, gradient sparsity, and oracle compatibility assumptions, and establishes performance bounds under local coverage and in-distribution reward accuracy. Experiments on several LLMs (Mistral, Llama, Gemma-2, Qwen3, Gemma-3) show that ComPO outperforms existing direct alignment methods, achieving higher length-controlled win rates and diagnostics that suggest mitigation of likelihood displacement.
The paper introduces Style‑Debiased DPO (SD‑DPO), a method that refines large language models’ ability to retrieve stored knowledge by using preference optimization that corrects for style differences while preserving factual accuracy. SD‑DPO evaluates on the EntiGraph storing‑side framework and outperforms baseline CPT on the QuALITY reading‑comprehension benchmark, achieving higher accuracy with far fewer training tokens. In a knowledge‑editing setting (AToKE), SD‑DPO attains an overall accuracy of 0.982, correctly answering queries with either new or old facts based on the requested time period.
arXiv:2607. 19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet.
arXiv:2607. 29283v1 Announce Type: cross Abstract: Training large language models (LLMs) to write register-transfer level (RTL) requires large corpora of paired specifications and code, and such data is scarce enough that most public corpora are now synthesized.
arXiv:2604. 27733v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human intent, whether through explicit reward modeling or direct methods such as DPO, fundamentally relies on minimizing a surrogate loss as a proxy for the true pairwise ranking objective.
arXiv:2610.19915v1 Announce Type: new Abstract: Rubric-based evaluation assesses the responses of large language models (LLMs) by aggregating the verification results of explicit criteria, yet not al...
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.