Aligner: Achieving Efficient Alignment through Weak-to-Strong Correction

Efforts to align Large Language Models (LLMs) are mainly conducted via Reinforcement Learning from Human Feedback (RLHF) methods. However, RLHF encounters major challenges including training reward models, actor-critic engineering, and importantly, it requires access to LLM parameters. Here we introduce Aligner, a new efficient alignment paradigm that bypasses the whole RLHF process by learning the correctional residuals between the aligned and the unaligned answers. Our Aligner offers several key advantages. Firstly, it is an autoregressive seq2seq model that is trained on the query-answer-correction dataset via supervised learning; this offers a parameter-efficient alignment solution with minimal resources. Secondly, the Aligner facilitates weak-to-strong generalization; finetuning large pretrained models by Aligner's supervisory signals demonstrates strong performance boost. Thirdly, Aligner functions as a model-agnostic plug-and-play module, allowing for its direct application on different open-source and API-based models. Remarkably, Aligner-7B improves 11 different LLMs by 21.9% in helpfulness and 23.8% in harmlessness on average (GPT-4 by 17.5% and 26.9%). When finetuning (strong) Llama2-70B with (weak) Aligner-13B's supervision, we can improve Llama2 by 8.2% in helpfulness and 61.6% in harmlessness. See our dataset and code at https://aligner2024.github.io

Panacea: Pareto Alignment via Preference Adaptation for LLMs

Current methods for large language model alignment typically use scalar human preference labels. However, this convention tends to oversimplify the multi-dimensional and heterogeneous nature of human preferences, leading to reduced expressivity and even misalignment. This paper presents Panacea, an innovative approach that reframes alignment as a multi-dimensional preference optimization problem. Panacea trains a single model capable of adapting online and Pareto-optimally to diverse sets of preferences without the need for further tuning. A major challenge here is using a low-dimensional preference vector to guide the model's behavior, despite it being governed by an overwhelmingly large number of parameters. To address this, Panacea is designed to use singular value decomposition (SVD)-based low-rank adaptation, which allows the preference vector to be simply injected online as singular values. Theoretically, we prove that Panacea recovers the entire Pareto front with common loss aggregation methods under mild conditions. Moreover, our experiments demonstrate, for the first time, the feasibility of aligning a single LLM to represent a spectrum of human preferences through various optimization methods. Our work marks a step forward in effectively and efficiently aligning models to diverse and intricate human preferences in a controllable and Pareto-optimal manner.

CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents

The generalization of decision-making agents encompasses two fundamental elements: learning from past experiences and reasoning in novel contexts. However, the predominant emphasis in most interactive environments is on learning, often at the expense of complexity in reasoning. In this paper, we introduce CivRealm, an environment inspired by the Civilization game. Civilization's profound alignment with human history and society necessitates sophisticated learning, while its ever-changing situations demand strong reasoning to generalize. Particularly, CivRealm sets up an imperfect-information general-sum game with a changing number of players; it presents a plethora of complex features, challenging the agent to deal with open-ended stochastic environments that require diplomacy and negotiation skills. Within CivRealm, we provide interfaces for two typical agent types: tensor-based agents that focus on learning, and language-based agents that emphasize reasoning. To catalyze further research, we present initial results for both paradigms. The canonical RL-based agents exhibit reasonable performance in mini-games, whereas both RL- and LLM-based agents struggle to make substantial progress in the full game. Overall, CivRealm stands as a unique learning and reasoning challenge for decision-making agents. The code is available at https://github.com/bigai-ai/civrealm.

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Built on offline RL algorithms, most O2O methods focus on the balance between RL objective and pessimism, or the utilization of offline and online samples. In this paper, from a novel perspective, we systematically study the challenges that remain in O2O RL and identify that the reason behind the slow improvement of the performance and the instability of online finetuning lies in the inaccurate Q-value estimation inherited from offline pretraining. Specifically, we demonstrate that the estimation bias and the inaccurate rank of Q-value cause a misleading signal for the policy update, making the standard offline RL algorithms, such as CQL and TD3-BC, ineffective in the online finetuning. Based on this observation, we address the problem of Q-value estimation by two techniques: (1) perturbed value update and (2) increased frequency of Q-value updates. The first technique smooths out biased Q-value estimation with sharp peaks, preventing early-stage policy exploitation of sub-optimal actions. The second one alleviates the estimation bias inherited from offline pretraining by accelerating learning. Extensive experiments on the MuJoco and Adroit environments demonstrate that the proposed method, named SO2, significantly alleviates Q-value estimation issues, and consistently improves the performance against the state-of-the-art methods by up to 83.1%.

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all within the popular yet challenging open-world Minecraft universe. Specifically, we develop JARVIS-1 on top of pre-trained multimodal language models, which map visual observations and textual instructions to plans. The plans will be ultimately dispatched to the goal-conditioned controllers. We outfit JARVIS-1 with a multimodal memory, which facilitates planning using both pre-trained knowledge and its actual game survival experiences. JARVIS-1 is the existing most general agent in Minecraft, capable of completing over 200 different tasks using control and observation space similar to humans. These tasks range from short-horizon tasks, e.g., "chopping trees" to long-horizon tasks, e.g., "obtaining a diamond pickaxe". JARVIS-1 performs exceptionally well in short-horizon tasks, achieving nearly perfect performance. In the classic long-term task of $\texttt{ObtainDiamondPickaxe}$, JARVIS-1 surpasses the reliability of current state-of-the-art agents by 5 times and can successfully complete longer-horizon and more challenging tasks. The project page is available at https://craftjarvis.org/JARVIS-1

AI Alignment: A Comprehensive Survey

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, the potential large-scale risks associated with misaligned AI systems become salient. Hundreds of AI experts and public figures have expressed concerns about AI risks, arguing that "mitigating the risk of extinction from AI should be a global priority, alongside other societal-scale risks such as pandemics and nuclear war". To provide a comprehensive and up-to-date overview of the alignment field, in this survey paper, we delve into the core concepts, methodology, and practice of alignment. We identify the RICE principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality. Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. Forward alignment and backward alignment form a recurrent process where the alignment of AI systems from the forward process is verified in the backward process, meanwhile providing updated objectives for forward alignment in the next round. On forward alignment, we discuss learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices that apply to every stage of AI systems' lifecycle. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.

Grasp Multiple Objects with One Hand

The human hand's complex kinematics allow for simultaneous grasping and manipulation of multiple objects, essential for tasks like object transfer and in-hand manipulation. Despite its importance, robotic multi-object grasping remains underexplored and presents challenges in kinematics, dynamics, and object configurations. This paper introduces MultiGrasp, a two-stage method for multi-object grasping on a tabletop with a multi-finger dexterous hand. It involves (i) generating pre-grasp proposals and (ii) executing the grasp and lifting the objects. Experimental results primarily focus on dual-object grasping and report a 44.13% success rate, showcasing adaptability to unseen object configurations and imprecise grasps. The framework also demonstrates the capability to grasp more than two objects, albeit at a reduced inference speed.

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.

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.

Safe RLHF: Safe Reinforcement Learning from Human Feedback

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness presents a significant challenge during LLM training. To address this issue, we propose Safe Reinforcement Learning from Human Feedback (Safe RLHF), a novel algorithm for human value alignment. Safe RLHF explicitly decouples human preferences regarding helpfulness and harmlessness, effectively avoiding the crowdworkers' confusion about the tension and allowing us to train separate reward and cost models. We formalize the safety concern of LLMs as an optimization task of maximizing the reward function while satisfying specified cost constraints. Leveraging the Lagrangian method to solve this constrained problem, Safe RLHF dynamically adjusts the balance between the two objectives during fine-tuning. Through a three-round fine-tuning using Safe RLHF, we demonstrate a superior ability to mitigate harmful responses while enhancing model performance compared to existing value-aligned algorithms. Experimentally, we fine-tuned the Alpaca-7B using Safe RLHF and aligned it with collected human preferences, significantly improving its helpfulness and harmlessness according to human evaluations.