Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

• URL: http://arxiv.org/abs/2410.19133v4
• Date: Fri, 23 May 2025 02:43:47 GMT
• Title: Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
• Authors: Lester James V. Miranda, Yizhong Wang, Yanai Elazar, Sachin Kumar, Valentina Pyatkin, Faeze Brahman, Noah A. Smith, Hannaneh Hajishirzi, Pradeep Dasigi,
• Abstract summary: We introduce HyPER, a Hybrid Preference routER that defers an annotation to either humans or language models (LMs)<n>We show that the selected hybrid mixture of synthetic and direct human preferences using HyPER achieves better RM performance compared to using either one exclusively by 7-13% on RewardBench.<n>We also analyze features from HyPER and find that prompts with moderate safety concerns or complexity benefit the most from human feedback.
• Score: 87.37721254914476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative is to distill preferences from LMs as a source of synthetic annotations, offering a cost-effective and scalable alternative, albeit susceptible to other biases and errors. In this work, we introduce HyPER, a Hybrid Preference routER that defers an annotation to either humans or LMs, achieving better annotation quality while reducing the cost of human-only annotation. We formulate this as an optimization problem: given a preference dataset and an evaluation metric, we (1) train a performance prediction model (PPM) to predict a reward model's (RM) performance on an arbitrary combination of human and LM annotations and (2) employ a routing strategy that selects a combination that maximizes the predicted performance. We train the PPM on MultiPref, a new preference dataset with 10k instances paired with humans and LM labels. We show that the selected hybrid mixture of synthetic and direct human preferences using HyPER achieves better RM performance compared to using either one exclusively by 7-13% on RewardBench and generalizes across unseen preference datasets and other base models. We also observe the same trend in other benchmarks using Best-of-N reranking, where the hybrid mix has 2-3% better performance. Finally, we analyze features from HyPER and find that prompts with moderate safety concerns or complexity benefit the most from human feedback.

Related papers

• Composable Cross-prompt Essay Scoring by Merging Models [7.5702468122067685]
  Cross-prompt automated essay scoring typically trains models jointly on all source prompts.<n>We propose a source-free adaptation approach that selectively merges individually trained source models' parameters instead of datasets.
  arXiv  Detail & Related papers  (2025-05-24T06:28:21Z)
• Rethinking Diverse Human Preference Learning through Principal Component Analysis [22.123631189289963]
  We introduce Decomposed Reward Models (DRMs), a novel approach that extracts diverse human preferences from binary comparisons. Our key insight is to represent human preferences as vectors and analyze them using Principal Component Analysis (PCA) DRMs effectively extract meaningful preference dimensions (e.g., helpfulness, safety, humor) and adapt to new users without additional training.
  arXiv  Detail & Related papers  (2025-02-18T18:55:26Z)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models [92.90660301195396]
  Calibrated Preference Optimization (CaPO) is a novel method to align text-to-image (T2I) diffusion models.<n>CaPO incorporates the general preference from multiple reward models without human annotated data.<n> Experimental results show that CaPO consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2025-02-04T18:59:23Z)
• Clear Preferences Leave Traces: Reference Model-Guided Sampling for Preference Learning [59.11519451499754]
  Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences.<n>Recent work has shown DPO's effectiveness relies on training data quality.<n>We discover that reference model probability space naturally detects high-quality training samples.
  arXiv  Detail & Related papers  (2025-01-25T07:21:50Z)
• RosePO: Aligning LLM-based Recommenders with Human Values [38.029251417802044]
  We propose a general framework -- Recommendation with smoothing personalized Preference Optimization (RosePO) RosePO better aligns with customized human values during the post-training stage. Evaluation on three real-world datasets demonstrates the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-10-16T12:54:34Z)
• Ordinal Preference Optimization: Aligning Human Preferences via NDCG [28.745322441961438]
  We develop an end-to-end preference optimization algorithm by approxing NDCG with a differentiable surrogate loss. OPO outperforms existing pairwise and listwise approaches on evaluation sets and general benchmarks like AlpacaEval.
  arXiv  Detail & Related papers  (2024-10-06T03:49:28Z)
• Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [64.67540769692074]
  Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date.<n>We introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models.<n>Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench.
  arXiv  Detail & Related papers  (2024-10-04T04:56:11Z)
• General Preference Modeling with Preference Representations for Aligning Language Models [51.14207112118503]
  We introduce preference representation learning, an approach that embeds responses into a latent space to capture intricate preference structures efficiently. We also propose preference score-based General Preference Optimization (GPO), which generalizes reward-based reinforcement learning from human feedback. Our method may enhance the alignment of foundation models with nuanced human values.
  arXiv  Detail & Related papers  (2024-10-03T04:22:55Z)
• Generative Reward Models [42.30530024761532]
  Reinforcement Learning from Human Feedback (RLHF) has greatly improved the performance of modern Large Language Models (LLMs) Recent work has shown that synthetic preferences labels may not align well with human preference judgments. We propose a hybrid approach that unifies RLHF and RLAIF methodologies. Our results show that combining the strengths of RLHF and RLAIF offers a promising approach for improving the quality of synthetic preference labels.
  arXiv  Detail & Related papers  (2024-10-02T17:58:39Z)
• Model-based Preference Optimization in Abstractive Summarization without Human Feedback [5.438770095369458]
  We introduce Model-based Preference Optimization (MPO) to fine-tune Large Language Models for improved summarization abilities without any human feedback. Our experiments on standard summarization datasets and various metrics demonstrate that our proposed MPO significantly enhances the quality of generated summaries without relying on human feedback.
  arXiv  Detail & Related papers  (2024-09-27T10:35:45Z)
• Hindsight Preference Learning for Offline Preference-based Reinforcement Learning [22.870967604847458]
  Offline preference-based reinforcement learning (RL) focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset. We propose to model human preferences using rewards conditioned on future outcomes of the trajectory segments. Our proposed method, Hindsight Preference Learning (HPL), can facilitate credit assignment by taking full advantage of vast trajectory data available in massive unlabeled datasets.
  arXiv  Detail & Related papers  (2024-07-05T12:05:37Z)
• PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences [6.398937923320069]
  We propose PAL, a framework to model human preference complementary to existing pretraining strategies. We show that PAL achieves competitive reward model accuracy compared to strong baselines.
  arXiv  Detail & Related papers  (2024-06-12T17:54:54Z)
• Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models (LLMs) with human preferences. Our key idea is leveraging the human prior knowledge within the small (seed) data. We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation [24.374185140811115]
  Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values. In this paper, we focus on addressing the issues due to the inherent heterogeneity in human preferences, as well as their potential strategic behavior in providing feedback. We propose two frameworks to address heterogeneous human feedback in principled ways: personalization-based one and aggregation-based one.
  arXiv  Detail & Related papers  (2024-04-30T23:57:23Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs.<n>Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• Dissecting Human and LLM Preferences [80.55271307662365]
  We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. We show that preference-based evaluation can be intentionally manipulated.
  arXiv  Detail & Related papers  (2024-02-17T14:34:31Z)
• AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model [69.12623428463573]
  AlignDiff is a novel framework to quantify human preferences, covering abstractness, and guide diffusion planning. It can accurately match user-customized behaviors and efficiently switch from one to another. We demonstrate its superior performance on preference matching, switching, and covering compared to other baselines.
  arXiv  Detail & Related papers  (2023-10-03T13:53:08Z)
• Models of human preference for learning reward functions [80.39289349661364]
  We learn the reward function from human-generated preferences between pairs of trajectory segments. We find this assumption to be flawed and propose modeling human preferences as informed by each segment's regret. Our proposed regret preference model better predicts real human preferences and also learns reward functions from these preferences that lead to policies that are better human-aligned.
  arXiv  Detail & Related papers  (2022-06-05T17:58:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.