There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their abilities to reason about the histories of their actions and observations. In this paper, we explore a new dimension in which large language models may benefit robotics planning. In particular, we propose Statler, a framework in which large language models are prompted to maintain an estimate of the world state, which are often unobservable, and track its transition as new actions are taken. Our framework then conditions each action on the estimate of the current world state. Despite being conceptually simple, our Statler framework significantly outperforms strong competing methods (e.g., Code-as-Policies) on several robot planning tasks. Additionally, it has the potential advantage of scaling up to more challenging long-horizon planning tasks. We release our code at https://github.com/ripl/statler

As Large Language Models (LLMs) become increasingly integrated into our everyday lives, understanding their ability to comprehend human mental states becomes critical for ensuring effective interactions. However, despite the recent attempts to assess the Theory-of-Mind (ToM) reasoning capabilities of LLMs, the degree to which these models can align with human ToM remains a nuanced topic of exploration. This is primarily due to two distinct challenges: (1) the presence of inconsistent results from previous evaluations, and (2) concerns surrounding the validity of existing evaluation methodologies. To address these challenges, we present a novel framework for procedurally generating evaluations with LLMs by populating causal templates. Using our framework, we create a new social reasoning benchmark (BigToM) for LLMs which consists of 25 controls and 5,000 model-written evaluations. We find that human participants rate the quality of our benchmark higher than previous crowd-sourced evaluations and comparable to expert-written evaluations. Using BigToM, we evaluate the social reasoning capabilities of a variety of LLMs and compare model performances with human performance. Our results suggest that GPT4 has ToM capabilities that mirror human inference patterns, though less reliable, while other LLMs struggle.

Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences. Thus, they can be seen as stochastic language layers in a language network, where the learnable parameters are the natural language prompts at each layer. By stacking two such layers and feeding the output of one layer to the next, we obtain a Deep Language Network (DLN). We first show how to effectively perform prompt optimization for a 1-Layer language network (DLN-1). Then, we present an extension that applies to 2-layer DLNs (DLN-2), where two prompts must be learned. The key idea is to consider the output of the first layer as a latent variable, which requires inference, and prompts to be learned as the parameters of the generative distribution. We first test the effectiveness of DLN-1 in multiple reasoning and natural language understanding tasks. Then, we show that DLN-2 can reach higher performance than a single layer, showing promise that we might reach comparable performance to GPT-4, even when each LLM in the network is smaller and less powerful.

They have shown a promising prospect in automatically completing tasks upon user instructions, functioning as brain-like coordinators. The associated risks will be revealed as we delegate an increasing number of tasks to machines for automated completion. A big question emerges: how can we make machines behave responsibly when helping humans automate tasks as personal copilots? In this paper, we explore this question in depth from the perspectives of feasibility, completeness and security. In specific, we present Responsible Task Automation (ResponsibleTA) as a fundamental framework to facilitate responsible collaboration between LLM-based coordinators and executors for task automation with three empowered capabilities: 1) predicting the feasibility of the commands for executors; 2) verifying the completeness of executors; 3) enhancing the security (e.g., the protection of users' privacy). We further propose and compare two paradigms for implementing the first two capabilities. One is to leverage the generic knowledge of LLMs themselves via prompt engineering while the other is to adopt domain-specific learnable models. Moreover, we introduce a local memory mechanism for achieving the third capability. We evaluate our proposed ResponsibleTA on UI task automation and hope it could bring more attentions to ensuring LLMs more responsible in diverse scenarios.

Injecting external knowledge can improve the performance of pre-trained language models (PLMs) on various downstream NLP tasks. However, massive retraining is required to deploy new knowledge injection methods or knowledge bases for downstream tasks. In this work, we are the first to study how to improve the flexibility and efficiency of knowledge injection by reusing existing downstream models. To this end, we explore a new paradigm plug-and-play knowledge injection, where knowledge bases are injected into frozen existing downstream models by a knowledge plugin. Correspondingly, we propose a plug-and-play injection method map-tuning, which trains a mapping of knowledge embeddings to enrich model inputs with mapped embeddings while keeping model parameters frozen. Experimental results on three knowledge-driven NLP tasks show that existing injection methods are not suitable for the new paradigm, while map-tuning effectively improves the performance of downstream models. Moreover, we show that a frozen downstream model can be well adapted to different domains with different mapping networks of domain knowledge. Our code and models are available at https://github.com/THUNLP/Knowledge-Plugin.

While the NLP community has produced numerous summarization benchmarks, none provide the rich annotations required to simultaneously address many important problems related to control and reliability. We introduce a Wikipedia-derived benchmark, complemented by a rich set of crowd-sourced annotations, that supports $8$ interrelated tasks: (i) extractive summarization; (ii) abstractive summarization; (iii) topic-based summarization; (iv) compressing selected sentences into a one-line summary; (v) surfacing evidence for a summary sentence; (vi) predicting the factual accuracy of a summary sentence; (vii) identifying unsubstantiated spans in a summary sentence; (viii) correcting factual errors in summaries. We compare various methods on this benchmark and discover that on multiple tasks, moderately-sized fine-tuned models consistently outperform much larger few-shot prompted language models. For factuality-related tasks, we also evaluate existing heuristics to create training data and find that training on them results in worse performance than training on $20\times$ less human-labeled data. Our articles draw from $6$ domains, facilitating cross-domain analysis. On some tasks, the amount of training data matters more than the domain where it comes from, while for other tasks training specifically on data from the target domain, even if limited, is more beneficial.

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides better initialization for other skills, improving the sample efficiency for skill learning. In skill planning, we leverage the prior knowledge in Large Language Models to find the relationships between skills and build a skill graph. When the agent is solving a task, our skill search algorithm walks on the skill graph and generates the proper skill plans for the agent. In experiments, our method accomplishes 40 diverse Minecraft tasks, where many tasks require sequentially executing for more than 10 skills. Our method outperforms baselines by a large margin and is the most sample-efficient demonstration-free RL method to solve Minecraft Tech Tree tasks. The project's website and code can be found at https://sites.google.com/view/plan4mc.

Content moderation at scale faces the challenge of considering local cultural distinctions when assessing content. While global policies aim to maintain decision-making consistency and prevent arbitrary rule enforcement, they often overlook regional variations in interpreting natural language as expressed in content. In this study, we are looking into how moderation systems can tackle this issue by adapting to local comprehension nuances. We train large language models on extensive datasets of media news and articles to create culturally attuned models. The latter aim to capture the nuances of communication across geographies with the goal of recognizing cultural and societal variations in what is considered offensive content. We further explore the capability of these models to generate explanations for instances of content violation, aiming to shed light on how policy guidelines are perceived when cultural and societal contexts change. We find that training on extensive media datasets successfully induced cultural awareness and resulted in improvements in handling content violations on a regional basis. Additionally, these advancements include the ability to provide explanations that align with the specific local norms and nuances as evidenced by the annotators' preference in our conducted study. This multifaceted success reinforces the critical role of an adaptable content moderation approach in keeping pace with the ever-evolving nature of the content it oversees.

While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with Pruning (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM. TAP utilizes an LLM to iteratively refine candidate (attack) prompts using tree-of-thoughts reasoning until one of the generated prompts jailbreaks the target. Crucially, before sending prompts to the target, TAP assesses them and prunes the ones unlikely to result in jailbreaks. Using tree-of-thought reasoning allows TAP to navigate a large search space of prompts and pruning reduces the total number of queries sent to the target. In empirical evaluations, we observe that TAP generates prompts that jailbreak state-of-the-art LLMs (including GPT4 and GPT4-Turbo) for more than 80% of the prompts using only a small number of queries. This significantly improves upon the previous state-of-the-art black-box method for generating jailbreaks.

Google has canceled its Gemini launch events scheduled for next week and now plans to launch its GPT-4 competitor in January, according to The Information. The company teased Gemini at I/O 2023, touting it then as a foundational model with "impressive multimodal capabilities" early in its training. Google initially planned to debut it before the end of the year in an unusually timed launch between the holidays -- which it didn't publicly announce -- but sources told The Information that Gemini was struggling with non-English queries, prompting CEO Sundar Pichai to delay its release. Gemini is intended to be able to handle a broad range of applications, combining different types of data like images and text for more advanced tasks. In May, Google said, "Once fine-tuned and rigorously tested for safety, Gemini will be available at various sizes and capabilities."