New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. C-Eval comprises multiple-choice questions across four difficulty levels: middle school, high school, college, and professional. The questions span 52 diverse disciplines, ranging from humanities to science and engineering. C-Eval is accompanied by C-Eval Hard, a subset of very challenging subjects in C-Eval that requires advanced reasoning abilities to solve. We conduct a comprehensive evaluation of the most advanced LLMs on C-Eval, including both English- and Chinese-oriented models. Results indicate that only GPT-4 could achieve an average accuracy of over 60%, suggesting that there is still significant room for improvement for current LLMs. We anticipate C-Eval will help analyze important strengths and shortcomings of foundation models, and foster their development and growth for Chinese users.

Our research investigates the recommendation of code examples to aid software developers, a practice that saves developers significant time by providing ready-to-use code snippets. The focus of our study is Stack Overflow, a commonly used resource for coding discussions and solutions, particularly in the context of the Java programming language. We applied BERT, a powerful Large Language Model (LLM) that enables us to transform code examples into numerical vectors by extracting their semantic information. Once these numerical representations are prepared, we identify Approximate Nearest Neighbors (ANN) using Locality-Sensitive Hashing (LSH). Our research employed two variants of LSH: Random Hyperplane-based LSH and Query-Aware LSH. We rigorously compared these two approaches across four parameters: HitRate, Mean Reciprocal Rank (MRR), Average Execution Time, and Relevance. Our study revealed that the Query-Aware (QA) approach showed superior performance over the Random Hyperplane-based (RH) method. Specifically, it exhibited a notable improvement of 20\% to 35\% in HitRate for query pairs compared to the RH approach. Furthermore, the QA approach proved significantly more time-efficient, with its speed in creating hashing tables and assigning data samples to buckets being at least four times faster. It can return code examples within milliseconds, whereas the RH approach typically requires several seconds to recommend code examples. Due to the superior performance of the QA approach, we tested it against PostFinder and FaCoY, the state-of-the-art baselines. Our QA method showed comparable efficiency proving its potential for effective code recommendation.

Vision-language alignment learned from image-caption pairs has been shown to benefit tasks like object recognition and detection. Methods are mostly evaluated in terms of how well object class names are learned, but captions also contain rich attribute context that should be considered when learning object alignment. It is unclear how methods use this context in learning, as well as whether models succeed when tasks require attribute and object understanding. To address this gap, we conduct extensive analysis of the role of attributes in vision-language models. We specifically measure model sensitivity to the presence and meaning of attribute context, gauging influence on object embeddings through unsupervised phrase grounding and classification via description methods. We further evaluate the utility of attribute context in training for open-vocabulary object detection, fine-grained text-region retrieval, and attribution tasks. Our results show that attribute context can be wasted when learning alignment for detection, attribute meaning is not adequately considered in embeddings, and describing classes by only their attributes is ineffective. A viable strategy that we find to increase benefits from attributes is contrastive training with adjective-based negative captions.

Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments. However, the evaluation of these models has often been performed in a scattered way on only one or two specific tasks, in a few languages, at a partial granularity (e.g., function) level, and in many cases without proper training data. Even more concerning is that in most cases the evaluation of generated codes has been done in terms of mere lexical overlap with a reference code rather than actual execution. We introduce xCodeEval, the largest executable multilingual multitask benchmark to date consisting of $25$M document-level coding examples ($16.5$B tokens) from about $7.5$K unique problems covering up to $11$ programming languages with execution-level parallelism. It features a total of $7$ tasks involving code understanding, generation, translation and retrieval. xCodeEval adopts an execution-based evaluation and offers a multilingual code execution engine, ExecEval that supports unit test based execution in all the $11$ languages. To address the challenge of balancing the distributions of text-code samples over multiple attributes in validation/test sets, we propose a novel data splitting and a data selection schema based on the geometric mean and graph-theoretic principle. Our experiments with OpenAI's LLMs (zero-shot) and open-LLMs (zero-shot and fine-tuned) on the tasks and languages demonstrate **xCodeEval** to be quite challenging as per the current advancements in language models.

Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does "linear representation" actually mean? And, how do we make sense of geometric notions (e.g., cosine similarity or projection) in the representation space? To answer these, we use the language of counterfactuals to give two formalizations of "linear representation", one in the output (word) representation space, and one in the input (sentence) space. We then prove these connect to linear probing and model steering, respectively. To make sense of geometric notions, we use the formalization to identify a particular (non-Euclidean) inner product that respects language structure in a sense we make precise. Using this causal inner product, we show how to unify all notions of linear representation. In particular, this allows the construction of probes and steering vectors using counterfactual pairs. Experiments with LLaMA-2 demonstrate the existence of linear representations of concepts, the connection to interpretation and control, and the fundamental role of the choice of inner product.

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable. These models appear to store vast amounts of knowledge from their training data, and to adapt quickly to new information provided in their context or prompt. We study how transformers balance these two types of knowledge by considering a synthetic setup where tokens are generated from either global or context-specific bigram distributions. By a careful empirical analysis of the training process on a simplified two-layer transformer, we illustrate the fast learning of global bigrams and the slower development of an "induction head" mechanism for the in-context bigrams. We highlight the role of weight matrices as associative memories, provide theoretical insights on how gradients enable their learning during training, and study the role of data-distributional properties.

It often feels like we're living in the future with technologies like artificial intelligence being so readily accessible. Nowhere is it more obvious than with ChatGPT, the consumer-facing AI that has simplified work and school for millions of people. And if you want to better understand ChatGPT and other AI technologies, The 2023 Ultimate AI ChatGPT & Python Programming Bundle can help. Between November 1st and 9th, you can get this 14-course bundle for an extra $10 off at just $29.97. This bundle offers introductory courses on Python, the world's most popular programming language and a core tool for artificial intelligence coding.

This paper presents a comprehensive evaluation of the code generation capabilities of ChatGPT, a prominent large language model, compared to human programmers. A novel dataset of 131 code-generation prompts across 5 categories was curated to enable robust analysis. Code solutions were generated by both ChatGPT and humans for all prompts, resulting in 262 code samples. A meticulous manual assessment methodology prioritized evaluating correctness, comprehensibility, and security using 14 established code quality metrics. The key findings reveal ChatGPT's strengths in crafting concise, efficient code with advanced constructs, showcasing strengths in data analysis tasks (93.1% accuracy) but limitations in visual-graphical challenges. Comparative analysis with human code highlights ChatGPT's inclination towards modular design and superior error handling. Additionally, machine learning models effectively distinguished ChatGPT from human code with up to 88% accuracy, suggesting detectable coding style disparities. By providing profound insights into ChatGPT's code generation capabilities and limitations through quantitative metrics and qualitative analysis, this study makes valuable contributions toward advancing AI-based programming assistants. The curated dataset and methodology offer a robust foundation for future research in this nascent domain. All data and codes are available on https://github.com/DSAatUSU/ChatGPT-promises-and-pitfalls.

Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from external data stores, but are challenging to build. Existing approaches require either expensive retrieval-specific modifications to LM pre-training or use post-hoc integration of the data store that leads to suboptimal performance. We introduce Retrieval-Augmented Dual Instruction Tuning (RA-DIT), a lightweight fine-tuning methodology that provides a third option by retrofitting any LLM with retrieval capabilities. Our approach operates in two distinct fine-tuning steps: (1) one updates a pre-trained LM to better use retrieved information, while (2) the other updates the retriever to return more relevant results, as preferred by the LM. By fine-tuning over tasks that require both knowledge utilization and contextual awareness, we demonstrate that each stage yields significant performance improvements, and using both leads to additional gains. Our best model, RA-DIT 65B, achieves state-of-the-art performance across a range of knowledge-intensive zero- and few-shot learning benchmarks, significantly outperforming existing in-context RALM approaches by up to +8.9% in 0-shot setting and +1.4% in 5-shot setting on average.

Deformable object manipulation stands as one of the most captivating yet formidable challenges in robotics. While previous techniques have predominantly relied on learning latent dynamics through demonstrations, typically represented as either particles or images, there exists a pertinent limitation: acquiring suitable demonstrations, especially for long-horizon tasks, can be elusive. Moreover, basing learning entirely on demonstrations can hamper the model's ability to generalize beyond the demonstrated tasks. In this work, we introduce a demonstration-free hierarchical planning approach capable of tackling intricate long-horizon tasks without necessitating any training. We employ large language models (LLMs) to articulate a high-level, stage-by-stage plan corresponding to a specified task. For every individual stage, the LLM provides both the tool's name and the Python code to craft intermediate subgoal point clouds. With the tool and subgoal for a particular stage at our disposal, we present a granular closed-loop model predictive control strategy. This leverages Differentiable Physics with Point-to-Point correspondence (DiffPhysics-P2P) loss in the earth mover distance (EMD) space, applied iteratively. Experimental findings affirm that our technique surpasses multiple benchmarks in dough manipulation, spanning both short and long horizons. Remarkably, our model demonstrates robust generalization capabilities to novel and previously unencountered complex tasks without any preliminary demonstrations. We further substantiate our approach with experimental trials on real-world robotic platforms.