Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a recent technique for eliciting complex multi-step reasoning through step-by-step answer examples, achieved the state-of-the-art performances in arithmetics and symbolic reasoning, difficult system-2 tasks that do not follow the standard scaling laws for LLMs. While these successes are often attributed to LLMs' ability for few-shot learning, we show that LLMs are decent zero-shot reasoners by simply adding Let's think step by step'' before each answer. Experimental results demonstrate that our Zero-shot-CoT, using the same single prompt template, significantly outperforms zero-shot LLM performances on diverse benchmark reasoning tasks including arithmetics (MultiArith, GSM8K, AQUA-RAT, SVAMP), symbolic reasoning (Last Letter, Coin Flip), and other logical reasoning tasks (Date Understanding, Tracking Shuffled Objects), without any hand-crafted few-shot examples, e.g. The versatility of this single prompt across very diverse reasoning tasks hints at untapped and understudied fundamental zero-shot capabilities of LLMs, suggesting high-level, multi-task broad cognitive capabilities may be extracted by simple prompting.

OpenAI's new model, called GPT-4b micro, was trained to suggest ways to re-engineer the protein factors to increase their function. According to OpenAI, researchers used the model's suggestions to change two of the Yamanaka factors to be more than 50 times as effective--at least according to some preliminary measures. "Just across the board, the proteins seem better than what the scientists were able to produce by themselves," says John Hallman, an OpenAI researcher. Hallman and OpenAI's Aaron Jaech, as well as Rico Meinl from Retro, were the model's lead developers. Outside scientists won't be able to tell if the results are real until they're published, something the companies say they are planning.

A groundbreaking chatbot created in the 1960s has been painstakingly reconstructed from archived records and run for the first time in over half a century, as part of an effort to preserve one of the earliest examples of artificial intelligence. ELIZA was written by computer scientist Joseph Weizenbaum at MIT in just 420 lines of code. The AI model is extremely rudimentary in comparison to today's large language models (LLMs) like ChatGPT but wowed researchers at the time with…

Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding benchmarks mostly consider a static instruction-to-code sequence transduction process, which has the potential for error propagation and a disconnect between the generated code and its final execution environment. To address this gap, we introduce InterCode, a lightweight, flexible, and easy-to-use framework of interactive coding as a standard reinforcement learning (RL) environment, with code as actions and execution feedback as observations. Our framework is language and platform agnostic, uses self-contained Docker environments to provide safe and reproducible execution, and is compatible out-of-the-box with traditional seq2seq coding methods, while enabling the development of new methods for interactive code generation. We use InterCode to create three interactive code environments with Bash, SQL, and Python as action spaces, leveraging data from the static NL2Bash, Spider, and MBPP datasets.

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting large language models (LLMs) to enhance task completion performance. The framework comprises two primary modules: the Swift module, representing fast and intuitive thinking, and the Sage module, emulating deliberate thought processes. The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding. We develop a heuristic method to harmoniously integrate the two modules, resulting in a more efficient and robust problem-solving process.

While large pretrained foundation models (FMs) have shown remarkable zero-shot classification robustness to dataset-level distribution shifts, their robustness to subpopulation or group shifts is relatively underexplored. We study this problem, and find that foundation models such as CLIP may not be robust to various group shifts. Unfortunately, existing methods to improve robustness require retraining, which can be prohibitively expensive on large foundation models. We also find that efficient ways to improve model inference (e.g. via adapters, lightweight networks that transform FM embeddings) do not consistently improve and can sometimes hurt group robustness compared to zero-shot. We therefore develop an adapter training strategy to effectively and efficiently improve FM group robustness.

Chain-of-thought prompting (CoT) and tool augmentation have been validated in recent work as effective practices for improving large language models (LLMs) to perform step-by-step reasoning on complex math-related tasks.However, most existing math reasoning datasets may not be able to fully evaluate and analyze the ability of LLMs in manipulating tools and performing reasoning, as they often only require very few invocations of tools or miss annotations for evaluating intermediate reasoning steps, thus supporting only outcome evaluation.To address the issue, we construct CARP, a new Chinese dataset consisting of 4,886 computation-intensive algebra problems with formulated annotations on intermediate steps, facilitating the evaluation of the intermediate reasoning process.In CARP, we test four LLMs with CoT prompting, and find that they are all prone to make mistakes at the early steps of the solution, leading to incorrect answers.Based on this finding, we propose a new approach that can facilitate the deliberation on reasoning steps with tool interfaces, namely DELI.In DELI, we first initialize a step-by-step solution based on retrieved exemplars, then iterate two deliberation procedures that check and refine the intermediate steps of the generated solution, from both tool manipulation and natural language reasoning perspectives, until solutions converge or the maximum iteration is achieved.Experimental results on CARP and six other datasets show that the proposed DELI mostly outperforms competitive baselines, and can further boost the performance of existing CoT methods.Our data and code are available at https://github.com/RUCAIBox/CARP.

Jonathan Lachman, the previous head of special projects at OpenAI, recently left to join a new artificial intelligence research lab founded by former OpenAI executive Mira Murati, according to two people familiar with the discussions. It's the most high-profile hire Murati has made since leaving OpenAI in September last year to start the much-hyped venture, which is focused on the exploration of so-called artificial general intelligence. Murati has poached roughly 10 researchers and engineers in total so far from competitors including OpenAI, Character AI, and Google DeepMind. Her startup is still in its early stages--it doesn't have a name, nor a firm product direction, according to two people familiar with the company. Murati and Lachman did not immediately respond to requests for comment.

This research introduces LegalScore, a specialized index for assessing how generative artificial intelligence models perform in a selected range of career exams that require a legal background in Brazil. The index evaluates fourteen different types of artificial intelligence models' performance, from proprietary to open-source models, in answering objective questions applied to these exams. The research uncovers the response of the models when applying English-trained large language models to Brazilian legal contexts, leading us to reflect on the importance and the need for Brazil-specific training data in generative artificial intelligence models. Performance analysis shows that while proprietary and most known models achieved better results overall, local and smaller models indicated promising performances due to their Brazilian context alignment in training. By establishing an evaluation framework with metrics including accuracy, confidence intervals, and normalized scoring, LegalScore enables systematic assessment of artificial intelligence performance in legal examinations in Brazil. While the study demonstrates artificial intelligence's potential value for exam preparation and question development, it concludes that significant improvements are needed before AI can match human performance in advanced legal assessments. The benchmark creates a foundation for continued research, highlighting the importance of local adaptation in artificial intelligence development.

In this report, we present DNA 1.0 8B Instruct, a state-of-the-art bilingual language model optimized for Korean and English language tasks. By applying continual pre-training (CPT) with high-quality Korean datasets to Llama 3.1 8B and subsequent supervised fine-tuning (SFT), we create an instruction-following model with enhanced Korean language capabilities. This model is then merged with Llama 3.1 8B Instruct via spherical linear interpolation (SLERP) and undergoes further optimization through direct preference optimization (DPO) and knowledge distillation (KD). DNA 1.0 8B Instruct achieves state-of-the-art results on Korean-specific tasks, including KMMLU (53.26%), KoBEST (83.40%), and BELEBELE (57.99%), while maintaining strong English capabilities on MMLU (66.64%), MMLU-Pro (43.05%) and GSM8K (80.52%). As an open model, DNA 1.0 8B Instruct represents a significant advancement in bilingual language modeling. As an open model, DNA 1.0 8B Instruct is freely available through https://huggingface.co/dnotitia/Llama-DNA-1.0-8B-Instruct . For commercial licensing inquiries or feedback, please contact us at https://www.dnotitia.com/contact/post-form