An official website of the United States government
Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a latent reward on the entire diffusion reverse chain, while ignoring the sequential nature of the generation process. From literature, this may harm the efficacy and efficiency of alignment. In this paper, we take on a finer dense reward perspective and derive a tractable alignment objective that emphasizes the initial steps of the T2I reverse chain. In particular, we introduce temporal discounting into the DPO-style explicit-reward-free loss, to break the temporal symmetry therein and suit the T2I generation hierarchy. In experiments on single and multiple prompt generation, our method is competitive with strong relevant baselines, both quantitatively and qualitatively. Further studies are conducted to illustrate the insight of our approach.
more »
« less
Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation
In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to dynamically adjust multiple reward weights during training. Through automatic and manual evaluations, we show that our proposed techniques, DynaOpt and C-DynaOpt, outperform existing naive and bandit baselines, showcasing their potential for enhancing language models.
more »
« less
- Award ID(s):
- 2306372
- PAR ID:
- 10616294
- Publisher / Repository:
- ELRA and ICCL
- Date Published:
- Format(s):
- Medium: X
- Location:
- Torino, Italia
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large language models are typically aligned with human preferences by optimizing reward models (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a composition of simpler reward models which each capture a different aspect of language quality. This itself presents a challenge, as it is difficult to appropriately weight these component RMs when combining them. Compounding this difficulty, because any RM is only a proxy for human evaluation, this process is vulnerable to overoptimization, wherein past a certain point, accumulating higher reward is associated with worse human ratings. In this paper, we perform, to our knowledge, the first study on overoptimization in composite RMs, showing that correlation between component RMs has a significant effect on the locations of these points. We then introduce an approach to solve this issue using constrained reinforcement learning as a means of preventing the agent from exceeding each RM’s threshold of usefulness. Our method addresses the problem of weighting component RMs by learning dynamic weights, naturally expressed by Lagrange multipliers. As a result, each RM stays within the range at which it is an effective proxy, improving evaluation performance. Finally, we introduce an adaptive method using gradient-free optimization to identify and optimize towards these points during a single run.more » « less
-
Banerjee, Arindam; Fukumizu, Kenji (Ed.)We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies, whose expected cumulative reward over the course of multiple rounds is maximum, and each one of them has an expected cost below a certain threshold. We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB), and prove a sublinear bound on its regret that is inversely proportional to the difference between the constraint threshold and the cost of a known feasible action. Our algorithm balances exploration and constraint satisfaction using a novel idea that scales the radii of the reward and cost confidence sets with different scaling factors. We further specialize our results to multi-armed bandits and propose a computationally efficient algorithm for this setting and prove a a regret bound that is better than simply casting multi-armed bandits as an instance of linear bandits and using the regret bound of OPLB. We also prove a lower-bound for the problem studied in the paper and provide simulations to validate our theoretical results. Finally, we show how our algorithm and analysis can be extended to multiple constraints and to the case when the cost of the feasible action is unknown.more » « less
-
Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.)In the stochastic contextual bandit setting, regret-minimizing algorithms have been extensively researched, but their instance-minimizing best-arm identification counterparts remain seldom studied. In this work, we focus on the stochastic bandit problem in the (ǫ, δ)-PAC setting: given a policy class Π the goal of the learner is to return a policy π ∈ Π whose expected reward is within ǫ of the optimal policy with probability greater than 1 − δ. We characterize the first instance-dependent PAC sample complexity of contextual bandits through a quantity ρΠ, and provide matching upper and lower bounds in terms of ρΠ for the agnostic and linear contextual best-arm identification settings. We show that no algorithm can be simultaneously minimax-optimal for regret minimization and instance-dependent PAC for best-arm identification. Our main result is a new instance-optimal and computationally efficient algorithm that relies on a polynomial number of calls to an argmax oracle.more » « less
-
Contextual bandit algorithms have become widely used for recommendation in online systems (e.g. marketplaces, music streaming, news), where they now wield substantial influence on which items get shown to users. This raises questions of fairness to the items — and to the sellers, artists, and writers that benefit from this exposure. We argue that the conventional bandit formulation can lead to an undesirable and unfair winner-takes-all allocation of exposure. To remedy this problem, we propose a new bandit objective that guarantees merit-based fairness of exposure to the items while optimizing utility to the users. We formulate fairness regret and reward regret in this setting and present algorithms for both stochastic multi-armed bandits and stochastic linear bandits. We prove that the algorithms achieve sublinear fairness regret and reward regret. Beyond the theoretical analysis, we also provide empirical evidence that these algorithms can allocate exposure to different arms effectively.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
