Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling

• URL: http://arxiv.org/abs/2407.02446v1
• Date: Tue, 2 Jul 2024 17:22:54 GMT
• Title: Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling
• Abstract summary: RLHF-aligned LMs have shown unprecedented ability on both benchmarks and long-form text generation. As RLHF models become agent models aimed at interacting with humans, they seem to lose their world modeling. We propose a potential explanation: to perform coherent long-form generation, RLHF models restrict randomness via implicit blueprints.
• Score: 34.3520410136648
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: RLHF-aligned LMs have shown unprecedented ability on both benchmarks and long-form text generation, yet they struggle with one foundational task: next-token prediction. As RLHF models become agent models aimed at interacting with humans, they seem to lose their world modeling -- the ability to predict what comes next in arbitrary documents, which is the foundational training objective of the Base LMs that RLHF adapts. Besides empirically demonstrating this trade-off, we propose a potential explanation: to perform coherent long-form generation, RLHF models restrict randomness via implicit blueprints. In particular, RLHF models concentrate probability on sets of anchor spans that co-occur across multiple generations for the same prompt, serving as textual scaffolding but also limiting a model's ability to generate documents that do not include these spans. We study this trade-off on the most effective current agent models, those aligned with RLHF, while exploring why this may remain a fundamental trade-off between models that act and those that predict, even as alignment techniques improve.

Related papers

• Scalable Offline Model-Based RL with Action Chunks [60.80151356018376]
  We study whether model-based reinforcement learning can provide a scalable recipe for tackling complex, long-horizon tasks in offline RL.<n>We call this recipe textbfModel-Based RL with Action Chunks (MAC).<n>We show that MAC achieves the best performance among offline model-based RL algorithms, especially on challenging long-horizon tasks.
  arXiv  Detail & Related papers  (2025-12-08T23:26:29Z)
• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models. We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization [18.892740849961456]
  Reinforcement Learning from Human Feedback (RLHF) has emerged as an important paradigm for aligning large language models with human preferences during post-training. This paper introduces Pairwise-RL, a RLHF framework that addresses these challenges through a combination of generative reward modeling and a pairwise proximal policy optimization algorithm.
  arXiv  Detail & Related papers  (2025-04-07T11:34:48Z)
• Provably Efficient Online RLHF with One-Pass Reward Modeling [59.30310692855397]
  We propose a one-pass reward modeling method that does not require storing the historical data and can be computed in constant time.<n>We provide theoretical guarantees showing that our method improves both statistical and computational efficiency.<n>We conduct experiments using Llama-3-8B-Instruct and Qwen2.5-7B-Instruct models on the Ultrafeedback-binarized and Mixture2 datasets.
  arXiv  Detail & Related papers  (2025-02-11T02:36:01Z)
• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging [65.41765072566287]
  We propose textbfDomain knowledtextbfge merged textbfReward textbfModel (DogeRM), a novel framework that integrates domain-specific knowledge into a general reward model by model merging.
  arXiv  Detail & Related papers  (2024-07-01T17:01:54Z)
• The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback [5.037876196534672]
  Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. In this paper, we illustrate the causes of this issue, reviewing relevant literature from model-based reinforcement learning, and argue for solutions.
  arXiv  Detail & Related papers  (2023-10-31T21:52:41Z)
• Non-autoregressive Conditional Diffusion Models for Time Series Prediction [3.9722979176564763]
  TimeDiff is a non-autoregressive diffusion model that achieves high-quality time series prediction. We show that TimeDiff consistently outperforms existing time series diffusion models.
  arXiv  Detail & Related papers  (2023-06-08T08:53:59Z)
• RRHF: Rank Responses to Align Language Models with Human Feedback without tears [69.68672043223249]
  InstructGPT implements RLHF through several stages, including Supervised Fine-Tuning (SFT), reward model training, and Proximal Policy Optimization (PPO) We propose a novel learning paradigm called RRHF, which scores sampled responses from different sources via a logarithm of conditional probabilities. We evaluate RRHF on the Helpful and Harmless dataset, demonstrating comparable alignment performance with PPO by reward model score and human labeling.
  arXiv  Detail & Related papers  (2023-04-11T15:53:40Z)
• Mismatched No More: Joint Model-Policy Optimization for Model-Based RL [172.37829823752364]
  We propose a single objective for jointly training the model and the policy, such that updates to either component increases a lower bound on expected return. Our objective is a global lower bound on expected return, and this bound becomes tight under certain assumptions. The resulting algorithm (MnM) is conceptually similar to a GAN.
  arXiv  Detail & Related papers  (2021-10-06T13:43:27Z)
• Reinforcement Learning as One Big Sequence Modeling Problem [84.84564880157149]
  Reinforcement learning (RL) is typically concerned with estimating single-step policies or single-step models. We view RL as a sequence modeling problem, with the goal being to predict a sequence of actions that leads to a sequence of high rewards.
  arXiv  Detail & Related papers  (2021-06-03T17:58:51Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

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.