Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

How to align large language models (LLMs) with user preferences from a static general dataset has been frequently studied. However, user preferences are usually personalized, changing, and diverse regarding culture, values, or time. This leads to the problem that the actual user preferences often do not coincide with those trained by the model developers in the practical use of LLMs. Since we cannot collect enough data and retrain for every demand, researching efficient real-time preference adaptation methods based on the backbone LLMs during test time is important. To this end, we introduce Amulet, a novel, training-free framework that formulates the decoding process of every token as a separate online learning problem with the guidance of simple user-provided prompts, thus enabling real-time optimization to satisfy users' personalized preferences. To reduce the computational cost brought by this optimization process for each token, we additionally provide a closed-form solution for each iteration step of the optimization process, thereby reducing the computational time cost to a negligible level. The detailed experimental results demonstrate that Amulet can achieve significant performance improvements in rich settings with combinations of different LLMs, datasets, and user preferences, while maintaining acceptable computational efficiency.

Retrieval Dexterity: Efficient Object Retrieval in Clutters with Dexterous Hand

Retrieving objects buried beneath multiple objects is not only challenging but also time-consuming. Performing manipulation in such environments presents significant difficulty due to complex contact relationships. Existing methods typically address this task by sequentially grasping and removing each occluding object, resulting in lengthy execution times and requiring impractical grasping capabilities for every occluding object. In this paper, we present a dexterous arm-hand system for efficient object retrieval in multi-object stacked environments. Our approach leverages large-scale parallel reinforcement learning within diverse and carefully designed cluttered environments to train policies. These policies demonstrate emergent manipulation skills (e.g., pushing, stirring, and poking) that efficiently clear occluding objects to expose sufficient surface area of the target object. We conduct extensive evaluations across a set of over 10 household objects in diverse clutter configurations, demonstrating superior retrieval performance and efficiency for both trained and unseen objects. Furthermore, we successfully transfer the learned policies to a real-world dexterous multi-fingered robot system, validating their practical applicability in real-world scenarios. Videos can be found on our project website https://ChangWinde.github.io/RetrDex.

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation

Refusal-Aware Instruction Tuning (RAIT) aims to enhance Large Language Models (LLMs) by improving their ability to refuse responses to questions beyond their knowledge, thereby reducing hallucinations and improving reliability. Effective RAIT must address two key challenges: firstly, effectively reject unknown questions to minimize hallucinations; secondly, avoid over-refusal to ensure questions that can be correctly answered are not rejected, thereby maintain the helpfulness of LLM outputs. In this paper, we address the two challenges by deriving insightful observations from the gradient-based perspective, and proposing the Gradient-driven Refusal Aware Instruction Tuning Framework GRAIT: (1) employs gradient-driven sample selection to effectively minimize hallucinations and (2) introduces an adaptive weighting mechanism during fine-tuning to reduce the risk of over-refusal, achieving the balance between accurate refusals and maintaining useful responses. Experimental evaluations on open-ended and multiple-choice question answering tasks demonstrate that GRAIT significantly outperforms existing RAIT methods in the overall performance. The source code and data will be available at https://github.com/opendatalab/GRAIT .

$β$-DQN: Improving Deep Q-Learning By Evolving the Behavior

While many sophisticated exploration methods have been proposed, their lack of generality and high computational cost often lead researchers to favor simpler methods like $\epsilon$-greedy. Motivated by this, we introduce $\beta$-DQN, a simple and efficient exploration method that augments the standard DQN with a behavior function $\beta$. This function estimates the probability that each action has been taken at each state. By leveraging $\beta$, we generate a population of diverse policies that balance exploration between state-action coverage and overestimation bias correction. An adaptive meta-controller is designed to select an effective policy for each episode, enabling flexible and explainable exploration. $\beta$-DQN is straightforward to implement and adds minimal computational overhead to the standard DQN. Experiments on both simple and challenging exploration domains show that $\beta$-DQN outperforms existing baseline methods across a wide range of tasks, providing an effective solution for improving exploration in deep reinforcement learning.

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors

Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives, often bypassing traditional reward-based defenses. Prior methods have primarily focused on reducing cumulative rewards; however, rewards are typically too generic to capture complex safety requirements effectively. As a result, focusing solely on reward reduction can lead to suboptimal attack strategies, particularly in safety-critical scenarios where more precise behavior manipulation is needed. To address these challenges, we propose RAT, a method designed for universal, targeted behavior attacks. RAT trains an intention policy that is explicitly aligned with human preferences, serving as a precise behavioral target for the adversary. Concurrently, an adversary manipulates the victim's policy to follow this target behavior. To enhance the effectiveness of these attacks, RAT dynamically adjusts the state occupancy measure within the replay buffer, allowing for more controlled and effective behavior manipulation. Our empirical results on robotic simulation tasks demonstrate that RAT outperforms existing adversarial attack algorithms in inducing specific behaviors. Additionally, RAT shows promise in improving agent robustness, leading to more resilient policies. We further validate RAT by guiding Decision Transformer agents to adopt behaviors aligned with human preferences in various MuJoCo tasks, demonstrating its effectiveness across diverse tasks.

Efficient Model-agnostic Alignment via Bayesian Persuasion

With recent advancements in large language models (LLMs), alignment has emerged as an effective technique for keeping LLMs consensus with human intent. Current methods primarily involve direct training through Supervised Fine-tuning (SFT) or Reinforcement Learning from Human Feedback (RLHF), both of which require substantial computational resources and extensive ground truth data. This paper explores an efficient method for aligning black-box large models using smaller models, introducing a model-agnostic and lightweight Bayesian Persuasion Alignment framework. We formalize this problem as an optimization of the signaling strategy from the small model's perspective. In the persuasion process, the small model (Advisor) observes the information item (i.e., state) and persuades large models (Receiver) to elicit improved responses. The Receiver then generates a response based on the input, the signal from the Advisor, and its updated belief about the information item. Through training using our framework, we demonstrate that the Advisor can significantly enhance the performance of various Receivers across a range of tasks. We theoretically analyze our persuasion framework and provide an upper bound on the Advisor's regret, confirming its effectiveness in learning the optimal signaling strategy. Our Empirical results demonstrates that GPT-2 can significantly improve the performance of various models, achieving an average enhancement of 16.1% in mathematical reasoning ability and 13.7% in code generation. We hope our work can provide an initial step toward rethinking the alignment framework from the Bayesian Persuasion perspective.

Incentive Compatibility for AI Alignment in Sociotechnical Systems: Positions and Prospects

The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety. While considerable strides have been made in addressing AI alignment challenges, existing methodologies primarily focus on technical facets, often neglecting the intricate sociotechnical nature of AI systems, which can lead to a misalignment between the development and deployment contexts. To this end, we posit a new problem worth exploring: Incentive Compatibility Sociotechnical Alignment Problem (ICSAP). We hope this can call for more researchers to explore how to leverage the principles of Incentive Compatibility (IC) from game theory to bridge the gap between technical and societal components to maintain AI consensus with human societies in different contexts. We further discuss three classical game problems for achieving IC: mechanism design, contract theory, and Bayesian persuasion, in addressing the perspectives, potentials, and challenges of solving ICSAP, and provide preliminary implementation conceptions.

Measuring Value Understanding in Language Models through Discriminator-Critique Gap

Recent advancements in Large Language Models (LLMs) have heightened concerns about their potential misalignment with human values. However, evaluating their grasp of these values is complex due to their intricate and adaptable nature. We argue that truly understanding values in LLMs requires considering both "know what" and "know why". To this end, we present the Value Understanding Measurement (VUM) framework that quantitatively assesses both "know what" and "know why" by measuring the discriminator-critique gap related to human values. Using the Schwartz Value Survey, we specify our evaluation values and develop a thousand-level dialogue dataset with GPT-4. Our assessment looks at both the value alignment of LLM's outputs compared to baseline answers and how LLM responses align with reasons for value recognition versus GPT-4's annotations. We evaluate five representative LLMs and provide strong evidence that the scaling law significantly impacts "know what" but not much on "know why", which has consistently maintained a high level. This may further suggest that LLMs might craft plausible explanations based on the provided context without truly understanding their inherent value, indicating potential risks.

Zero-shot Preference Learning for Offline RL via Optimal Transport

Preference-based Reinforcement Learning (PbRL) has demonstrated remarkable efficacy in aligning rewards with human intentions. However, a significant challenge lies in the need of substantial human labels, which is costly and time-consuming. Additionally, the expensive preference data obtained from prior tasks is not typically reusable for subsequent task learning, leading to extensive labeling for each new task. In this paper, we propose a novel zero-shot preference-based RL algorithm that leverages labeled preference data from source tasks to infer labels for target tasks, eliminating the requirement for human queries. Our approach utilizes Gromov-Wasserstein distance to align trajectory distributions between source and target tasks. The solved optimal transport matrix serves as a correspondence between trajectories of two tasks, making it possible to identify corresponding trajectory pairs between tasks and transfer the preference labels. However, learning directly from inferred labels that contains a fraction of noisy labels will result in an inaccurate reward function, subsequently affecting policy performance. To this end, we introduce Robust Preference Transformer, which models the rewards as Gaussian distributions and incorporates reward uncertainty in addition to reward mean. The empirical results on robotic manipulation tasks of Meta-World and Robomimic show that our method has strong capabilities of transferring preferences between tasks and learns reward functions from noisy labels robustly. Furthermore, we reveal that our method attains near-oracle performance with a small proportion of scripted labels.