Distilling explicit chain-of-thought reasoning paths has emerged as an effective method for improving the reasoning abilities of large language models (LLMs) across various tasks. However, when tackling complex tasks that pose significant challenges for state-of-the-art models, this technique often struggles to produce effective chains of thought that lead to correct answers. In this work, we propose a novel approach to distill reasoning abilities from LLMs by leveraging their capacity to explain solutions. We apply our method to solving competitive-level programming challenges. More specifically, we employ an LLM to generate explanations for a set of <problem, solution-program> pairs, then use <problem, explanation> pairs to fine-tune a smaller language model, which we refer to as the Reasoner, to learn algorithmic reasoning that can generate "how-to-solve" hints for unseen problems. Our experiments demonstrate that learning from explanations enables the Reasoner to more effectively guide program implementation by a Coder, resulting in higher solve rates than strong chain-of-thought baselines on competitive-level programming problems. It also outperforms models that learn directly from <problem, solution-program> pairs. We curated an additional test set in the CodeContests format, which includes 246 more recent problems posted after the models' knowledge cutoff.
The ability to interact with machines using natural human language is becoming not just commonplace, but expected. The next step is not just text interfaces, but speech interfaces and not just with computers, but with all machines including robots. In this paper, we chronicle the recent history of this growing field of spoken dialogue with robots and offer the community three proposals, the first focused on education, the second on benchmarks, and the third on the modeling of language when it comes to spoken interaction with robots. The three proposals should act as white papers for any researcher to take and build upon.
In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method. We investigate the practical utility of two advanced planning methods, iterative correction and tree search. We present a comprehensive analysis of how discrimination accuracy affects the overall performance of agents when using these two methods or a simpler method, re-ranking. Experiments on two tasks, text-to-SQL parsing and mathematical reasoning, show that: (1) advanced planning methods demand discriminators with at least 90% accuracy to achieve significant improvements over re-ranking; (2) current LLMs' discrimination abilities have not met the needs of advanced planning methods to achieve such improvements; (3) with LLM-based discriminators, advanced planning methods may not adequately balance accuracy and efficiency. For example, compared to the other two methods, tree search is at least 10--20 times slower but leads to negligible performance gains, which hinders its real-world applications. Code and data will be released at https://github.com/OSU-NLP-Group/llm-planning-eval.
Traditional information retrieval is based on sparse bag-of-words vector representations of documents and queries. More recent deep-learning approaches have used dense embeddings learned using a transformer-based large language model. We show that on a classic benchmark on scientific document retrieval in the medical domain of cystic fibrosis, that both of these models perform roughly equivalently. Notably, dense vectors from the state-of-the-art SPECTER2 model do not significantly enhance performance. However, a hybrid model that we propose combining these methods yields significantly better results, underscoring the merits of integrating classical and contemporary deep learning techniques in information retrieval in the domain of specialized scientific documents.
There is growing interest in generating skeleton-based human motions from natural language descriptions. While most efforts have focused on developing better neural architectures for this task, there has been no significant work on determining the proper evaluation metric. Human evaluation is the ultimate accuracy measure for this task, and automated metrics should correlate well with human quality judgments. Since descriptions are compatible with many motions, determining the right metric is critical for evaluating and designing effective generative models. This paper systematically studies which metrics best align with human evaluations and proposes new metrics that align even better. Our findings indicate that none of the metrics currently used for this task show even a moderate correlation with human judgments on a sample level. However, for assessing average model performance, commonly used metrics such as R-Precision and less-used coordinate errors show strong correlations. Additionally, several recently developed metrics are not recommended due to their low correlation compared to alternatives. We also introduce a novel metric based on a multimodal BERT-like model, MoBERT, which offers strongly human-correlated sample-level evaluations while maintaining near-perfect model-level correlation. Our results demonstrate that this new metric exhibits extensive benefits over all current alternatives.
In this paper, we approach competitive-level programming problem-solving as a composite task of reasoning and code generation. We propose a novel method to automatically annotate natural language explanations to \textit{<problem, solution>} pairs. We show that despite poor performance in solving competitive-level programming problems, state-of-the-art LLMs exhibit a strong capacity in describing and explaining solutions. Our explanation generation methodology can generate a structured solution explanation for the problem containing descriptions and analysis. To evaluate the quality of the annotated explanations, we examine their effectiveness in two aspects: 1) satisfying the human programming expert who authored the oracle solution, and 2) aiding LLMs in solving problems more effectively. The experimental results on the CodeContests dataset demonstrate that while LLM GPT3.5's and GPT-4's abilities in describing the solution are comparable, GPT-4 shows a better understanding of the key idea behind the solution.
Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing that token-level edits are out of context and sometimes ambiguous, we propose building clause-level edit models instead. Besides, while most language models of code are not specifically pre-trained for SQL, they know common data structures and their operations in programming languages such as Python. Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code. Our error correction model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines. Our code and data are available at https://github.com/OSU-NLP-Group/Auto-SQL-Correction.
Answering questions about why characters perform certain actions is central to understanding and reasoning about narratives. Despite recent progress in QA, it is not clear if existing models have the ability to answer "why" questions that may require commonsense knowledge external to the input narrative. In this work, we introduce TellMeWhy, a new crowd-sourced dataset that consists of more than 30k questions and free-form answers concerning why characters in short narratives perform the actions described. For a third of this dataset, the answers are not present within the narrative. Given the limitations of automated evaluation for this task, we also present a systematized human evaluation interface for this dataset. Our evaluation of state-of-the-art models show that they are far below human performance on answering such questions. They are especially worse on questions whose answers are external to the narrative, thus providing a challenge for future QA and narrative understanding research.
Efforts are underway at UT Austin to build autonomous robot systems that address the challenges of long-term deployments in office environments and of the more prescribed domestic service tasks of the RoboCup@Home competition. We discuss the contrasts and synergies of these efforts, highlighting how our work to build a RoboCup@Home Domestic Standard Platform League entry led us to identify an integrated software architecture that could support both projects. Further, naturalistic deployments of our office robot platform as part of the Building-Wide Intelligence project have led us to identify and research new problems in a traditional laboratory setting.
Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual semantic captioning model that can describe a large number of object categories not present in existing image-caption datasets. Our model takes advantage of external sources -- labeled images from object recognition datasets, and semantic knowledge extracted from unannotated text. We propose minimizing a joint objective which can learn from these diverse data sources and leverage distributional semantic embeddings, enabling the model to generalize and describe novel objects outside of image-caption datasets. We demonstrate that our model exploits semantic information to generate captions for hundreds of object categories in the ImageNet object recognition dataset that are not observed in MSCOCO image-caption training data, as well as many categories that are observed very rarely. Both automatic evaluations and human judgements show that our model considerably outperforms prior work in being able to describe many more categories of objects.