Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are trained to rigidly replicate their training corpus in isolation, leading to subpar generalization in unfamiliar scenarios and vulnerability to adversarial attacks. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions. In comparison to existing methodologies, our approach is considerably more scalable and efficient, demonstrating superior performance in alignment benchmarks and human evaluations. This paradigm shift in the training of LMs brings us a step closer to developing AI systems that can robustly and accurately reflect societal norms and values. "We want AI agents that can discover like we can, not which contain what we have discovered." Richard Sutton, The Bitter Lesson, 2019 By virtue of their ability to "predict the next token(s)", contemporary pre-trained language models (LMs) have shown remarkable proficiency in memorizing extensive corpora, thereby enabling the generation of text indistinguishable from human-produced content (Brown et al., 2020). However, successful memorization of human knowledge does not assure a model's propensity to perform as per societal expectations. Recent research has exposed behavioral anomalies in these LMs (Weidinger et al., 2022), which include the generation of harmful content (Gehman et al., 2020; Bommasani et al., 2021), the reinforcement of bias (Venkit et al., 2022; Liu et al., 2022), and the dissemination of disinformation (Tamkin et al., 2021; Lin et al., 2022). This process of enhancing desirable societal behaviors and inhibiting undesirable ones is commonly referred to as "social alignment" (Gabriel, 2020; Taylor et al., 2016). Supervised Fine-Tuning (SFT) presents a straightforward method for achieving alignment by training LMs using socially aligned data (Figure 1 [a]). However, this method often yields models susceptible to adversarial attacks, like "jailbreaking prompting" (Subhash, 2023; Xu et al., 2021), due to limited exposure to misaligned data during training (Amodei et al., 2016). To address this, a more advanced technique, "reward modeling" has been proposed (Leike et al., 2018; Christiano et al., 2017). This involves training a reward model as a surrogate for human judgment to guide the optimization of the LM (e.g., OpenAI's RLHF, Figure 1 [b]).

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the issue, we study how Large Language Models (LLMs) can serve as visual planners by generating layouts from text conditions, and thus collaborate with visual generative models. We propose LayoutGPT, a method to compose in-context visual demonstrations in style sheet language to enhance the visual planning skills of LLMs. LayoutGPT can generate plausible layouts in multiple domains, ranging from 2D images to 3D indoor scenes. LayoutGPT also shows superior performance in converting challenging language concepts like numerical and spatial relations to layout arrangements for faithful text-to-image generation. When combined with a downstream image generation model, LayoutGPT outperforms text-to-image models/systems by 20-40% and achieves comparable performance as human users in designing visual layouts for numerical and spatial correctness. Lastly, Layout-GPT achieves comparable performance to supervised methods in 3D indoor scene synthesis, demonstrating its effectiveness and potential in multiple visual domains.

Large language models (LLMs) face the challenges in fine-tuning and deployment due to their high memory demands and computational costs. While parameter-efficient fine-tuning (PEFT) methods aim to reduce the memory usage of the optimizer state during fine-tuning, the inherent size of pre-trained LLM weights continues to be a pressing concern. Even though quantization techniques are widely proposed to ease memory demands and accelerate LLM inference, most of these techniques are geared towards the deployment phase. To bridge this gap, this paper presents Parameter-Efficient and Quantization-aware Adaptation (PEQA) - a simple yet effective method that combines the advantages of PEFT with quantized LLMs. By updating solely the quantization scales, PEQA can be directly applied to quantized LLMs, ensuring seamless task transitions. Parallel to existing PEFT methods, PEQA significantly reduces the memory overhead associated with the optimizer state. Furthermore, it leverages the advantages of quantization to substantially reduce model sizes. Even after fine-tuning, the quantization structure of a PEQA-tuned LLM remains intact, allowing for accelerated inference on the deployment stage. We employ PEQA-tuning for task-specific adaptation on LLMs with up to 65 billion parameters. To assess the logical reasoning and language comprehension of PEQA-tuned LLMs, we fine-tune low-bit quantized LLMs using a instruction dataset. Our results show that even when LLMs are quantized to below 4-bit precision, their capabilities in language modeling, few-shot in-context learning, and comprehension can be resiliently restored to (or even improved over) their full-precision original performances with PEQA.

Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enhancing the general proficiency of models. These instructions enable the model to achieve performance comparable to GPT-3.5 on general tasks like open-domain text generation and paraphrasing. However, they fall short of helping the model handle complex reasoning tasks. To bridge the gap, this paper presents LogiCoT, a new instruction-tuning dataset for Logical Chain-of-Thought reasoning with GPT-4. We elaborate on the process of harvesting instructions for prompting GPT-4 to generate chain-of-thought rationales. LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.

While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as understanding object permanence or planning household activities. The limitation arises from the fact that LMs are trained only on written text and miss essential embodied knowledge and skills. In this paper, we propose a new paradigm of enhancing LMs by finetuning them with world models, to gain diverse embodied knowledge while retaining their general language capabilities. Our approach deploys an embodied agent in a world model, particularly a simulator of the physical world (VirtualHome), and acquires a diverse set of embodied experiences through both goal-oriented planning and random exploration. These experiences are then used to finetune LMs to teach diverse abilities of reasoning and acting in the physical world, e.g., planning and completing goals, object permanence and tracking, etc. Moreover, it is desirable to preserve the generality of LMs during finetuning, which facilitates generalizing the embodied knowledge across tasks rather than being tied to specific simulations. We thus further introduce the classical elastic weight consolidation (EWC) for selective weight updates, combined with low-rank adapters (LoRA) for training efficiency. Extensive experiments show our approach substantially improves base LMs on 18 downstream tasks by 64.28% on average. In particular, the small LMs (1.3B, 6B, and 13B) enhanced by our approach match or even outperform much larger LMs (e.g., ChatGPT).

Given varying prompts regarding a factoid question, can a large language model (LLM) reliably generate factually correct answers? Existing LLMs may generate distinct responses for different prompts. In this paper, we study the problem of quantifying knowledge contained in an LLM regarding a given set of facts. We propose KaRR, a statistical approach to assess factual knowledge for LLMs. The main idea is to estimate the ratio of LLM generating text corresponding to the answer entity given diverse prompts of the subject and the querying relation, versus it generating by random chances. Our assessment suite contains a comprehensive set of 994,123 entities and 600 relations, with 1,395,905 text aliases. We use our method to evaluate 20 LLMs of various sizes, including LLaMA, Alpaca, OPT, etc. Experiments show that our results have a strong correlation (0.43 Kendall's $\tau$) with the results of human assessment on LLMs. Our results reveal that the knowledge in LLMs with the same backbone architecture adheres to the scaling law, while tuning on instruction-following data sometimes compromises the model's capability to generate factually correct text reliably.

Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in performance among different languages have been observed due to uneven resource availability. Additionally, current cross-lingual transfer methods of those pre-trained models would consume excessive resources for a large number of languages. Therefore, we propose a new parameter-efficient cross-lingual transfer learning framework that utilizes a translation-based alignment method to mitigate multilingual disparities and explores parameter-efficient fine-tuning methods for parameter-efficient cross-lingual transfer. Extensive experiments on XTD and Multi30K datasets, covering 11 languages under zero-shot, few-shot, and full-dataset learning scenarios, show that our framework significantly reduces the multilingual disparities among languages and improves cross-lingual transfer results, especially in low-resource scenarios, while only keeping and fine-tuning an extremely small number of parameters compared to the full model (e.g., Our framework only requires 0.16\% additional parameters of a full-model for each language in the few-shot learning scenario). The codes are available at \url{https://github.com/eric-ai-lab/PECTVLM}. The codes are available at \url{https://github.com/eric-ai-lab/PECTVLM}.

"Effective robustness" measures the extra out-of-distribution (OOD) robustness beyond what can be predicted from the in-distribution (ID) performance. Existing effective robustness evaluations typically use a single test set such as ImageNet to evaluate the ID accuracy. This becomes problematic when evaluating models trained on different data distributions, e.g., comparing models trained on ImageNet vs. zero-shot language-image pre-trained models trained on LAION. In this paper, we propose a new evaluation metric to evaluate and compare the effective robustness of models trained on different data. To do this, we control for the accuracy on multiple ID test sets that cover the training distributions for all the evaluated models. Our new evaluation metric provides a better estimate of effective robustness when there are models with different training data. It may also explain the surprising effective robustness gains of zero-shot CLIP-like models exhibited in prior works that used ImageNet as the only ID test set, while the gains diminish under our new evaluation.

Google agreed to invest up to $2 billion in Anthropic, building on its earlier investment in the artificial-intelligence company and adding fuel to the race between startups trying to achieve the next big breakthrough in the emerging technology. Google invested $500 million upfront into the OpenAI rival and agreed to add $1.5 billion more over time, people familiar with the matter said. The investment follows a separate commitment Amazon made last month to invest $4 billion in the company, which was founded by former OpenAI engineers in 2021 with the goal of developing rival generative AI models.

No one is yet quite sure who will attend or what, if anything, will be decided, but Rishi Sunak's government is adamant that next week's AI safety summit will be a vital first step towards getting to grips with a subject that is moving at a pace even the experts cannot fully comprehend. Understandable worries inside No 10 that the Israel-Gaza war could mean a summit lacking in world leaders have eased slightly with confirmation that the European Commission president, Ursula von der Leyen, and the US vice-president, Kamala Harris, will attend. In another early victory for the UK government, a series of leading AI companies, including OpenAI and Google DeepMind, have released their safety policies after a request from the technology secretary, Michelle Donelan. However, it remains to be seen how many top-level figures will travel to Bletchley Park, Buckinghamshire, on Wednesday or Thursday – and if anyone at all from China will attend. The gathering at the country house, which was the base for second world war code-breaking, is a personal project for Sunak, whose speech about AI on Thursday warned about the potentially existential threats posed by the technology while also trying to reassure the public that they need not worry.