Large language models (LLMs) have exhibited remarkable capabilities in learning from expla- nations in prompts, but there has been limited understanding of exactly how these explana- tions function or why they are effective. This work aims to better understand the mechanisms by which explanations are used for in-context learning. We first study the impact of two dif- ferent factors on the performance of prompts with explanations: the computation trace (the way the solution is decomposed) and the natural language used to express the prompt. By per- turbing explanations on three controlled tasks, we show that both factors contribute to the ef- fectiveness of explanations. We further study how to form maximally effective sets of expla- nations for solving a given test query. We find that LLMs can benefit from the complemen- tarity of the explanation set: diverse reasoning skills shown by different exemplars can lead to better performance. Therefore, we propose a maximal marginal relevance-based exemplar selection approach for constructing exemplar sets that are both relevant as well as comple- mentary, which successfully improves the in- context learning performance across three real- world tasks on multiple LLMs.

Language models can memorize a considerable amount of factual information during pretraining that can be elicited through prompting or finetuning models on tasks like question answering. In this paper, we discuss approaches to measuring model factual beliefs, updating incorrect factual beliefs in models, and visualizing graphical relationships between factual beliefs. Our main contributions include: (1) new metrics for evaluating belief-updating methods focusing on the logical consistency of beliefs, (2) a training objective for Sequential, Local, and Generalizing updates (SLAG) that improves the performance of existing hypernetwork approaches, and (3) the introduction of the belief graph, a new form of visualization for language models that shows relationships between stored model beliefs. Our experiments suggest that models show only limited consistency between factual beliefs, but update methods can both fix incorrect model beliefs and greatly improve their consistency. Although off-the-shelf optimizers are surprisingly strong belief-updating baselines, our learned optimizers can outperform them in more difficult settings than have been considered in past work.

Hate speech detection is complex; it relies on commonsense reasoning, knowledge of stereotypes, and an understanding of social nuance that differs from one culture to the next. It is also difficult to collect a large-scale hate speech annotated dataset. In this work, we frame this problem as a few-shot learning task, and show significant gains with decomposing the task into its “constituent” parts. In addition, we see that infusing knowledge from reasoning datasets (e.g. ATOMIC2020) improves the performance even further. Moreover, we observe that the trained models generalize to out-of-distribution datasets, showing the superiority of task decomposition and knowledge infusion compared to previously used methods. Concretely, our method outperforms the baseline by 17.83% absolute gain in the 16-shot case.

Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings: in- and out-of-domain language modeling, zero- and few-shot priming, and full-shot fine-tuning. With the exception of fine-tuning, we find MoEs to be substantially more compute efficient. At more modest training budgets, MoEs can match the performance of dense models using ~4 times less compute. This gap narrows at scale, but our largest MoE model (1.1T parameters) consistently outperforms a compute-equivalent dense model (6.7B parameters). Overall, this performance gap varies greatly across tasks and domains, suggesting that MoE and dense models generalize differently in ways that are worthy of future study. We make our code and models publicly available for research use.

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. Extractive summarization systems, though interpretable, suffer from redundancy and possible lack of coherence. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary. Our framework can be applied to any evidence-based text generation problem and can accommodate various pretrained models in its simple architecture. We use the Information Bottleneck principle to jointly train the extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans and then generates a summary using only the evidence. Using automatic and human evaluations, we show that the generated summaries are better than strong extractive and extractive-abstractive baselines.

State-of-the-art Machine Reading Comprehension (MRC) models for Open-domain Question Answering (QA) are typically trained for span selection using distantly supervised positive examples and heuristically retrieved negative examples. This training scheme possibly explains empirical observations that these models achieve a high recall amongst their top few predictions, but a low overall accuracy, motivating the need for answer re-ranking. We develop a successful re-ranking approach (RECONSIDER) for span-extraction tasks that improves upon the performance of MRC models, even beyond large-scale pre-training. RECONSIDER is trained on positive and negative examples extracted from high confidence MRC model predictions, and uses in-passage span annotations to perform span-focused re-ranking over a smaller candidate set. As a result, RECONSIDER learns to eliminate close false positives, achieving a new extractive state of the art on four QA tasks, with 45.5% Exact Match accuracy on Natural Questions with real user questions, and 61.7% on TriviaQA. We will release all related data, models, and code.

We present ELQ, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass. Evaluated on WebQSP and GraphQuestions with extended annotations that cover multiple entities per question, ELQ outperforms the previous state of the art by a large margin of +12.7% and +19.6% F1, respectively. With a very fast inference time (1.57 examples/s on a single CPU), ELQ can be useful for downstream question answering systems. In a proof-of-concept experiment, we demonstrate that using ELQ significantly improves the downstream QA performance of GraphRetriever.

Programmers typically organize executable source code using high-level coding patterns or idiomatic structures such as nested loops, exception handlers and recursive blocks, rather than as individual code tokens. In contrast, state of the art (SOTA) semantic parsers still map natural language instructions to source code by building the code syntax tree one node at a time. In this paper, we introduce an iterative method to extract code idioms from large source code corpora by repeatedly collapsing most-frequent depth-2 subtrees of their syntax trees, and train semantic parsers to apply these idioms during decoding. Applying idiom-based decoding on a recent context-dependent semantic parsing task improves the SOTA by 2.2% BLEU score while reducing training time by more than 50%. This improved speed enables us to scale up the model by training on an extended training set that is 5× larger, to further move up the SOTA by an additional 2.3% BLEU and 0.9% exact match. Finally, idioms also significantly improve accuracy of semantic parsing to SQL on the ATIS-SQL dataset, when training data is limited.

Interactive programming with interleaved code snippet cells and natural language markdown is recently gaining popularity in the form of Jupyter notebooks, which accelerate prototyping and collaboration. To study code generation conditioned on a long context history, we present JuICe, a corpus of 1.5 million examples with a curated test set of 3.7K instances based on online programming assignments. Compared with existing contextual code generation datasets, JuICe provides refined human-curated data, open-domain code, and an order of magnitude more training data. Using JuICe, we train models for two tasks: (1) generation of the API call sequence in a code cell, and (2) full code cell generation, both conditioned on the NL-Code history up to a particular code cell. Experiments using current baseline code generation models show that both context and distant supervision aid in generation, and that the dataset is challenging for current systems.

We propose a context-dependent model to map utterances within an interaction to executable formal queries. To incorporate interaction history, the model maintains an interaction-level encoder that updates after each turn, and can copy sub-sequences of previously predicted queries during generation. Our approach combines implicit and explicit modeling of references between utterances. We evaluate our model on the ATIS flight planning interactions, and demonstrate the benefits of modeling context and explicit references.

Source code is rarely written in isolation. It depends significantly on the programmatic context, such as the class that the code would reside in. To study this phenomenon, we introduce the task of generating class member functions given English documentation and the programmatic context provided by the rest of the class. This task is challenging because the desired code can vary greatly depending on the functionality the class provides (e.g., a sort function may or may not be available when we are asked to “return the smallest element” in a particular member variable list). We introduce CONCODE, a new large dataset with over 100,000 examples consisting of Java classes from online code repositories, and develop a new encoder-decoder architecture that models the interaction between the method documentation and the class environment. We also present a detailed error analysis suggesting that there is significant room for future work on this task.

Semantic parsing, the study of translating natural language utterances into machine-executable programs, is a well-established research area and has applications in question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically with the introduction of neural encoder-decoder methods that allow us to rethink many of the previous assumptions underlying semantic parsing. We aim to inform those already interested in semantic parsing research of these new developments in the field, as well as introduce the topic as an exciting research area to those who are unfamiliar with it. Current approaches for neural semantic parsing share several similarities with neural machine translation, but the key difference between the two fields is that semantic parsing translates natural language into a formal language, while machine translation translates it into a different natural language. The formal language used in semantic parsing allows for constrained decoding, where the model is constrained to only produce outputs that are valid formal statements. We will describe the various approaches researchers have taken to do this. We will also discuss the choice of formal languages used by semantic parsers, and describe why much recent work has chosen to use standard programming languages instead of more linguistically-motivated representations. We will then describe a particularly challenging setting for semantic parsing, where there is additional context or interaction that the parser must take into account when translating natural language to formal language, and give an overview of recent work in this direction. Finally, we will introduce some tools available in AllenNLP for doing semantic parsing research.

Sequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text using Abstract Meaning Representation (AMR) has been limited, due to the relatively limited amount of labeled data and the non-sequential nature of the AMR graphs. We present a novel training procedure that can lift this limitation using millions of unlabeled sentences and careful preprocessing of the AMR graphs. For AMR parsing, our model achieves competitive results of 62.1 SMATCH, the current best score reported without significant use of external semantic resources. For AMR generation, our model establishes a new state-of-the-art performance of BLEU 33.8. We present extensive ablative and qualitative analysis including strong evidence that sequence-based AMR models are robust against ordering variations of graph-to-sequence conversions.

We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural sequence models to map utterances directly to SQL with its full expressivity, bypassing any intermediate meaning representations. These models are immediately deployed online to solicit feedback from real users to flag incorrect queries. Finally, the popularity of SQL facilitates gathering annotations for incorrect predictions using the crowd, which is directly used to improve our models. This complete feedback loop, without intermediate representations or database specific engineering, opens up new ways of building high quality semantic parsers. Experiments suggest that this approach can be deployed quickly for any new target domain, as we show by learning a semantic parser for an online academic database from scratch.