We’ve fine-tuned the 774M parameter GPT-2 language model using human feedback for various tasks, successfully matching the preferences of the external human labelers, though those preferences did not always match our own. Specifically, for summarization tasks the labelers preferred sentences copied wholesale from the input (we’d only asked them to ensure accuracy), so our models learned to copy.
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
arXiv:2205. 11930v3 Announce Type: replace-cross Abstract: Human ratings are the gold standard in NLG evaluation.
arXiv:2606. 06614v1 Announce Type: cross Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data.
arXiv:2601. 19792v4 Announce Type: replace-cross Abstract: For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical.
arXiv:2606. 11166v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks.
arXiv:2601. 02813v3 Announce Type: replace Abstract: Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize.
arXiv:2502. 20502v2 Announce Type: replace Abstract: Recent advances in Artificial Intelligence (AI) have yielded powerful computational models that, by learning from vast amounts of human-generated data, are increasingly posited as approximate models of human cognition.
arXiv:2606. 07629v1 Announce Type: cross Abstract: Current approaches to aligning large language models (LLMs) aggregate diverse human preferences into a single reward signal, effectively optimizing for a hypothetical ``average user'' who represents no real person particularly well.
arXiv:2606. 12754v1 Announce Type: cross Abstract: Are large language models (LLMs) bad at capturing human judgment?
arXiv:2607. 17524v1 Announce Type: cross Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task.
arXiv:2602. 03160v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles.
arXiv:2511. 21140v4 Announce Type: replace Abstract: Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators.