Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields. While several prior works have investigated solving elementary mathematics using LLMs, this work explores the frontier of using GPT-4 for solving more complex and challenging math problems. We evaluate various ways of using GPT-4. Some of them are adapted from existing work, and one is MathChat, a conversational problem-solving framework newly proposed in this work. We perform the evaluation on difficult high school competition problems from the MATH dataset, which shows the advantage of the proposed conversational approach.

Many recent efforts aim to augment language models with relevant information retrieved from a database at test time. We avoid the need for prompt engineering by directly fine-tuning the model on data retrieved at test time using its standard training setup. For this purpose, we build a large-scale distributed nearest neighbor index based on text embeddings of the Pile dataset. Given a query to a language model, our system retrieves the neighbors of the query and fine-tunes the model on the text data corresponding to those neighbors. Surprisingly, retrieving and training on as few as 20 neighbors, each for only one gradient iteration, drastically improves performance across more than twenty language modeling tasks in the Pile benchmark. For example, test-time training significantly narrows the performance gap between a small GPT2 model and a GPTNeo model, more than ten times larger, that was specifically trained to convergence on the Pile. Sufficient index quality and size, however, are important. Our work establishes a valuable first baseline for implementing test-time training in the context of large language models, opening the door to numerous promising research avenues.

Content Warning: This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups.} Large pre-trained language models are acknowledged to carry social biases towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and categorize social biases in Text-to-SQL models. We summarize the categories of social biases that may occur in structured data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social biases at very different rates. We show how to take advantage of our methodology to uncover and assess social biases in the downstream Text-to-SQL task. We will release our code and data.

Prompt engineering relevance research has seen a notable surge in recent years, primarily driven by advancements in pre-trained language models and large language models. However, a critical issue has been identified within this domain: the inadequate of sensitivity and robustness of these models towards Prompt Templates, particularly in lesser-studied languages such as Japanese. This paper explores this issue through a comprehensive evaluation of several representative Large Language Models (LLMs) and a widely-utilized pre-trained model(PLM). These models are scrutinized using a benchmark dataset in Japanese, with the aim to assess and analyze the performance of the current multilingual models in this context. Our experimental results reveal startling discrepancies. A simple modification in the sentence structure of the Prompt Template led to a drastic drop in the accuracy of GPT-4 from 49.21 to 25.44. This observation underscores the fact that even the highly performance GPT-4 model encounters significant stability issues when dealing with diverse Japanese prompt templates, rendering the consistency of the model's output results questionable. In light of these findings, we conclude by proposing potential research trajectories to further enhance the development and performance of Large Language Models in their current stage.

Large language models (LLMs) have recently received significant attention for their exceptional capabilities. Despite extensive efforts in developing general-purpose LLMs that can be utilized in various natural language processing (NLP) tasks, there has been less research exploring their potential in recommender systems. In this paper, we propose a novel framework, named PALR, which aiming to combine user history behaviors (such as clicks, purchases, ratings, etc.) with LLMs to generate user preferred items. Specifically, we first use user/item interactions as guidance for candidate retrieval. Then we adopt a LLM-based ranking model to generate recommended items. Unlike existing approaches that typically adopt general-purpose LLMs for zero/few-shot recommendation testing or training on small-sized language models (with less than 1 billion parameters), which cannot fully elicit LLMs' reasoning abilities and leverage rich item side parametric knowledge, we fine-tune a 7 billion parameters LLM for the ranking purpose. This model takes retrieval candidates in natural language format as input, with instruction which explicitly asking to select results from input candidates during inference. Our experimental results demonstrate that our solution outperforms state-of-the-art models on various sequential recommendation tasks.

We introduce Alexa Arena, a user-centric simulation platform for Embodied AI (EAI) research. Alexa Arena provides a variety of multi-room layouts and interactable objects, for the creation of human-robot interaction (HRI) missions. With user-friendly graphics and control mechanisms, Alexa Arena supports the development of gamified robotic tasks readily accessible to general human users, thus opening a new venue for high-efficiency HRI data collection and EAI system evaluation. Along with the platform, we introduce a dialog-enabled instruction-following benchmark and provide baseline results for it. We make Alexa Arena publicly available to facilitate research in building generalizable and assistive embodied agents.

Humans naturally exploit haptic feedback during contact-rich tasks like loading a dishwasher or stocking a bookshelf. Current robotic systems focus on avoiding unexpected contact, often relying on strategically placed environment sensors. Recently, contact-exploiting manipulation policies have been trained in simulation and deployed on real robots. However, they require some form of real-world adaptation to bridge the sim-to-real gap, which might not be feasible in all scenarios. In this paper we train a contact-exploiting manipulation policy in simulation for the contact-rich household task of loading plates into a slotted holder, which transfers without any fine-tuning to the real robot. We investigate various factors necessary for this zero-shot transfer, like time delay modeling, memory representation, and domain randomization. Our policy transfers with minimal sim-to-real gap and significantly outperforms heuristic and learnt baselines. It also generalizes to plates of different sizes and weights. Demonstration videos and code are available at https://sites.google.com/view/compliant-object-insertion.

Large language models (LLMs) can acquire strong code-generation capabilities through few-shot learning. In contrast, supervised fine-tuning is still needed for smaller models to achieve good performance. Such fine-tuning demands a large number of task-specific NL-code pairs, which are expensive to obtain. In this paper, we attempt to transfer the code generation ability of an LLM to a smaller model with the aid of weakly-supervised data. More specifically, we propose explicit knowledge transfer (EKT), which uses the few-shot capabilities of a teacher LLM to create NL-code pairs that we then filter for correctness and fine-tune the student on. We evaluate EKT on the task of generating code solutions to math word problems from the GSM8k dataset. We find that EKT not only yields better performance than training with expert iteration, but also outperforms knowledge distillation, another form of knowledge transfer. A GPT-Neo 1.3B model trained using EKT with a GPT-J teacher achieves a 12.4% pass@100 on GSM8k, while the same student and teacher trained with knowledge distillation yield only a 3.7% pass@100. We also show that it is possible for a student model to outperform the teacher using EKT.

We have recently witnessed a number of impressive results on hard mathematical reasoning problems with language models. At the same time, the robustness of these models has also been called into question; recent works have shown that models can rely on shallow patterns in the problem description when generating a solution. Building on the idea of behavioral testing, we propose a novel framework, which pins down the causal effect of various factors in the input, e.g., the surface form of the problem text, the operands, and math operators on the output solution. By grounding the behavioral analysis in a causal graph describing an intuitive reasoning process, we study the behavior of language models in terms of robustness and sensitivity to direct interventions in the input space. We apply our framework on a test bed of math word problems. Our analysis shows that robustness does not appear to continuously improve as a function of size, but the GPT-3 Davinci models (175B) achieve a dramatic improvement in both robustness and sensitivity compared to all other GPT variants.

Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize the underexplored task of translating saliency maps into natural language and compare methods that address two key challenges of this approach -- what and how to verbalize. In both automatic and human evaluation setups, using token-level attributions from text classification tasks, we compare two novel methods (search-based and instruction-based verbalizations) against conventional feature importance representations (heatmap visualizations and extractive rationales), measuring simulatability, faithfulness, helpfulness and ease of understanding. Instructing GPT-3.5 to generate saliency map verbalizations yields plausible explanations which include associations, abstractive summarization and commonsense reasoning, achieving by far the highest human ratings, but they are not faithfully capturing numeric information and are inconsistent in their interpretation of the task. In comparison, our search-based, model-free verbalization approach efficiently completes templated verbalizations, is faithful by design, but falls short in helpfulness and simulatability. Our results suggest that saliency map verbalization makes feature attribution explanations more comprehensible and less cognitively challenging to humans than conventional representations.