Is it sensical to ascribe psychological predicates to AI systems like chatbots based on large language models (LLMs)? People have intuitively started ascribing emotions or consciousness to social AI ('affective artificial agents'), with consequences that range from love to suicide. The philosophical question of whether such ascriptions are warranted is thus very relevant. This paper advances the argument that LLMs instantiate language users in Ludwig Wittgenstein's sense but that ascribing psychological predicates to these systems remains a functionalist temptation. Social AIs are not full-blown language users, but rather more like Italo Calvino's literature machines. The ideas of LLMs as Wittgensteinian language users and Calvino's literature-producing writing machine are combined. This sheds light on the misguided functionalist temptation inherent in moving from equating the two to the ascription of psychological predicates to social AI. Finally, the framework of mortal computation is used to show that social AIs lack the basic autopoiesis needed for narrative fa\c{c}ons de parler and their role in the sensemaking of human (inter)action. Such psychological predicate ascriptions could make sense: the transition 'from quantity to quality' can take place, but its route lies somewhere between life and death, not between affective artifacts and emotion approximation by literature machines.

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work by emulating the preferences at the single decision (turn) level, limiting their capabilities in settings that require planning or multi-turn interactions to achieve a long-term goal. In this paper, we address this issue by developing novel methods for Reinforcement Learning (RL) from preference feedback between two full multi-turn conversations. In the tabular setting, we present a novel mirror-descent-based policy optimization algorithm for the general multi-turn preference-based RL problem, and prove its convergence to Nash equilibrium. To evaluate performance, we create a new environment, Education Dialogue, where a teacher agent guides a student in learning a random topic, and show that a deep RL variant of our algorithm outperforms RLHF baselines. Finally, we show that in an environment with explicit rewards, our algorithm recovers the same performance as a reward-based RL baseline, despite relying solely on a weaker preference signal.

The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL). However, such a collection manner poses a privacy threat, and one potential solution is Federated Learning (FL), which transfers gradients, not raw data, among clients. Unlike traditional networks, FL for LLMs incurs significant communication costs due to their tremendous parameters. This study introduces an innovative approach to compress gradients to improve communication efficiency during LLM FL, formulating the new FL pipeline named CG-FedLLM. This approach integrates an encoder on the client side to acquire the compressed gradient features and a decoder on the server side to reconstruct the gradients. We also developed a novel training strategy that comprises Temporal-ensemble Gradient-Aware Pre-training (TGAP) to identify characteristic gradients of the target model and Federated AutoEncoder-Involved Fine-tuning (FAF) to compress gradients adaptively. Extensive experiments confirm that our approach reduces communication costs and improves performance (e.g., average 3 points increment compared with traditional CL- and FL-based fine-tuning with LlaMA on a well-recognized benchmark, C-Eval). This improvement is because our encoder-decoder, trained via TGAP and FAF, can filter gradients while selectively preserving critical features. Furthermore, we present a series of experimental analyses focusing on the signal-to-noise ratio, compression rate, and robustness within this privacy-centric framework, providing insight into developing more efficient and secure LLMs.

Reinforcement Learning (RL)-Based Recommender Systems (RSs) have gained rising attention for their potential to enhance long-term user engagement. However, research in this field faces challenges, including the lack of user-friendly frameworks, inconsistent evaluation metrics, and difficulties in reproducing existing studies. To tackle these issues, we introduce EasyRL4Rec, an easy-to-use code library designed specifically for RL-based RSs. This library provides lightweight and diverse RL environments based on five public datasets and includes core modules with rich options, simplifying model development. It provides unified evaluation standards focusing on long-term outcomes and offers tailored designs for state modeling and action representation for recommendation scenarios. Furthermore, we share our findings from insightful experiments with current methods. EasyRL4Rec seeks to facilitate the model development and experimental process in the domain of RL-based RSs. The library is available for public use.

We need to look at our shoelaces as we first learn to tie them but having mastered this skill, we can do it from touch alone. We call this phenomenon "sensory scaffolding": observation streams that are not needed by a master might yet aid a novice learner. We consider such sensory scaffolding setups for training artificial agents. For example, a robot arm may need to be deployed with just a low-cost, robust, general-purpose camera; yet its performance may improve by having privileged training-time-only access to informative albeit expensive and unwieldy motion capture rigs or fragile tactile sensors. For these settings, we propose Scaffolder, a reinforcement learning approach which effectively exploits privileged sensing in critics, world models, reward estimators, and other such auxiliary components that are only used at training time, to improve the target policy. For evaluating sensory scaffolding agents, we design a new "S3" suite of ten diverse simulated robotic tasks that explore a wide range of practical sensor setups. Agents must use privileged camera sensing to train blind hurdlers, privileged active visual perception to help robot arms overcome visual occlusions, privileged touch sensors to train robot hands, and more. Scaffolder easily outperforms relevant prior baselines and frequently performs comparably even to policies that have test-time access to the privileged sensors. It is well-known that Beethoven composed symphonies long after he had fully lost his hearing. Such feats are commonly held to be evidence of mastery: for example, novice typists need to look at the keyboard to locate keys but with practice, can graduate to typing without looking. Thus, sensing requirements may be different during learning versus after learning. We refer to this as "sensory scaffolding", drawing inspiration from the concept of scaffolding teaching mechanisms in psychology that provide temporary support for a student (Wood et al., 1976; Vygotsky et al., 2011), like training wheels when learning to ride a bicycle. For artificial learning agents such as robots, sensory scaffolding permits decoupling the observation streams required at test time from those that are used to train the agent. The sensors available in a deployed robot are often decided by practical considerations such as cost, robustness, size, compute requirements, and ease of instrumentation, e.g., autonomous cars with only cheap and robust RGB camera sensors. However, those considerations might carry less weight at training time, so a robot learning practitioner may choose to scaffold policy learning with privileged information (Vapnik & Vashist, 2009) from extra sensors available only at training. In the case of the cars above, the manufacturer might equip a small fleet of training cars with expensive privileged sensors like lidar to improve RGB-only driving policies for customers to install in their cars.

Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose a paradigm to efficiently harvest 10 million naturally existing instruction data from the pre-training web corpus to enhance LLM reasoning. Our approach involves (1) recalling relevant documents, (2) extracting instruction-response pairs, and (3) refining the extracted pairs using open-source LLMs. Fine-tuning base LLMs on this dataset, we build MAmmoTH2 models, which significantly boost performance on reasoning benchmarks. Notably, MAmmoTH2-7B's (Mistral) performance increases from 11% to 36.7% on MATH and from 36% to 68.4% on GSM8K without training on any in-domain data. Further training MAmmoTH2 on public instruction tuning datasets yields MAmmoTH2-Plus, achieving state-of-the-art performance on several reasoning and chatbot benchmarks. Our work demonstrates how to harvest large-scale, high-quality instruction data without costly human annotation or GPT-4 distillation, providing a new paradigm for building better instruction tuning data.

In this paper, we explore the design and use of conversational telepresence robots to help homebound older adults interact with the external world. An initial needfinding study (N=8) using video vignettes revealed older adults' experiential needs for robot-mediated remote experiences such as exploration, reminiscence and social participation. We then designed a prototype system to support these goals and conducted a technology probe study (N=11) to garner a deeper understanding of user preferences for remote experiences. The study revealed user interactive patterns in each desired experience, highlighting the need of robot guidance, social engagements with the robot and the remote bystanders. Our work identifies a novel design space where conversational telepresence robots can be used to foster meaningful interactions in the remote physical environment. We offer design insights into the robot's proactive role in providing guidance and using dialogue to create personalized, contextualized and meaningful experiences.

Recent advances in large language models have shown capabilities that are extraordinary and near-superhuman. These models operate with such complexity that reliably evaluating and aligning them proves challenging for humans. This leads to the natural question: can guidance from weak models (like humans) adequately direct the capabilities of strong models? In a recent and somewhat surprising work, Burns et al. (2023) empirically demonstrated that when strong models (like GPT-4) are finetuned using labels generated by weak supervisors (like GPT-2), the strong models outperform their weaker counterparts -- a phenomenon they term weak-to-strong generalization. In this work, we present a theoretical framework for understanding weak-to-strong generalization. Specifically, we show that the improvement in performance achieved by strong models over their weaker counterparts is quantified by the misfit error incurred by the strong model on labels generated by the weaker model. Our theory reveals several curious algorithmic insights. For instance, we can predict the amount by which the strong model will improve over the weak model, and also choose among different weak models to train the strong model, based on its misfit error. We validate our theoretical findings through various empirical assessments.

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. However, current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. In this study, we introduce LOVA3, an innovative framework named ``Learning tO Visual Question Answering, Asking and Assessment,'' designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming at fostering the skills of asking and assessing questions in the context of images. To develop the questioning ability, we compile a comprehensive set of multimodal foundational tasks. For assessment, we introduce a new benchmark called EvalQABench, comprising 64,000 training samples (split evenly between positive and negative samples) and 5,000 testing samples. We posit that enhancing MLLMs with the capabilities to answer, ask, and assess questions will improve their multimodal comprehension and lead to better performance. We validate our hypothesis by training an MLLM using the LOVA3 framework and testing it on 10 multimodal benchmarks. The results demonstrate consistent performance improvements, thereby confirming the efficacy of our approach.

Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or benchmark in a fully supervised manner. While the dense occupancy grids need point-wise semantic annotations, which incur expensive and tedious labeling costs. In this paper, we build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. In particular, we propose a simple yet effective approach called Scribble2Scene, which bridges the gap between the sparse scribble annotations and fully-supervision. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance. Experiments on SemanticKITTI demonstrate that Scribble2Scene achieves competitive performance against the fully-supervised counterparts, showing 99% performance of the fully-supervised models with only 13.5% voxels labeled. Both annotations of ScribbleSC and our full implementation are available at https://github.com/songw-zju/Scribble2Scene.