Contemporary Large Language Models (LLMs) exhibit a high degree of code generation and comprehension capability. A particularly promising area is their ability to interpret code modules from unfamiliar libraries for solving user-instructed tasks. Recent work has shown that large proprietary LLMs can learn novel library usage in-context from demonstrations. These results raise several open questions: whether demonstrations of library usage is required, whether smaller (and more open) models also possess such capabilities, etc. In this work, we take a broader approach by systematically evaluating a diverse array of LLMs across three scenarios reflecting varying levels of domain specialization to understand their abilities and limitations in generating code based on libraries defined in-context. Our results show that even smaller open-source LLMs like Llama-2 and StarCoder demonstrate an adept understanding of novel code libraries based on specification presented in-context. Our findings further reveal that LLMs exhibit a surprisingly high proficiency in learning novel library modules even when provided with just natural language descriptions or raw code implementations of the functions, which are often cheaper to obtain than demonstrations. Overall, our results pave the way for harnessing LLMs in more adaptable and dynamic coding environments.

In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a pre-trained dense retrieval model to bypass this limitation, giving the model only a partial view of the full label space for each inference call. Testing with recent open-source LLMs (OPT, LLaMA), we set new state of the art performance in few-shot settings for three common intent classification datasets, with no fine-tuning. We also surpass fine-tuned performance on fine-grained sentiment classification in certain cases. We analyze the performance across number of in-context examples and different model scales, showing that larger models are necessary to effectively make use of larger context lengths for ICL. By running several ablations, we analyze the model’s use of: a) the similarity of the in-context examples to the current input, b) the semantic content of the class names, and c) the correct correspondence between examples and labels. We demonstrate that all three are needed to varying degrees depending on the domain, contrary to certain recent works.

Humans possess a remarkable ability to assign novel interpretations to linguistic expressions, enabling them to learn new words and understand community-specific connotations. However, Large Language Models (LLMs) have a knowledge cutoff and are costly to finetune repeatedly. Therefore, it is crucial for LLMs to learn novel interpretations in-context. In this paper, we systematically analyse the ability of LLMs to acquire novel interpretations using in-context learning. To facilitate our study, we introduce MAGNIFICo, an evaluation suite implemented within a text-to-SQL semantic parsing framework that incorporates diverse tokens and prompt settings to simulate real-world complexity. Experimental results on MAGNIFICo demonstrate that LLMs exhibit a surprisingly robust capacity for comprehending novel interpretations from natural language descriptions as well as from discussions within long conversations. Nevertheless, our findings also highlight the need for further improvements, particularly when interpreting unfamiliar words or when composing multiple novel interpretations simultaneously in the same example. Additionally, our analysis uncovers the semantic predispositions in LLMs and reveals the impact of recency bias for information presented in long contexts.

Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training data. Recent work often tackles this problem using large language models (LLMs) like GPT3 that can generate new examples given already available ones. In this work, we propose a method to generate more helpful augmented data by utilizing the LLM’s abilities to follow instructions and perform few-shot classifications. Our specific PromptMix method consists of two steps: 1) generate challenging text augmentations near class boundaries; however, generating borderline examples increases the risk of false positives in the dataset, so we 2) relabel the text augmentations using a prompting-based LLM classifier to enhance the correctness of labels in the generated data. We evaluate the proposed method in challenging 2-shot and zero-shot settings on four text classification datasets: Banking77, TREC6, Subjectivity (SUBJ), and Twitter Complaints. Our experiments show that generating and, crucially, relabeling borderline examples facilitates the transfer of knowledge of a massive LLM like GPT3.5-turbo into smaller and cheaper classifiers like DistilBERT-base and BERT-base. Furthermore, 2-shot PromptMix outperforms multiple 5-shot data augmentation methods on the four datasets. Our code is available at https://github.com/ServiceNow/PromptMix-EMNLP-2023.

Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data for intent classification with off-the-shelf language models (LMs) such as GPT-3. An advantage of this method is that no task-specific LM-fine-tuning for data generation is required; hence the method requires no hyper parameter tuning and is applicable even when the available training data is very scarce. We evaluate the proposed method in a few-shot setting on four diverse intent classification tasks. We find that GPT-generated data significantly boosts the performance of intent classifiers when intents in consideration are sufficiently distinct from each other. In tasks with semantically close intents, we observe that the generated data is less helpful. Our analysis shows that this is because GPT often generates utterances that belong to a closely-related intent instead of the desired one. We present preliminary evidence that a prompting-based GPT classifier could be helpful in filtering the generated data to enhance its quality.

Pretrained large generative language models have shown great performance on many tasks, but exhibit low compositional generalization abilities. Scaling such models has been shown to improve their performance on various NLP tasks even just by conditioning them on a few examples to solve the task without any fine-tuning (also known as in-context learning). In this work, we look at the gap between the in-distribution (ID) and out-of-distribution (OOD) performance of such models in semantic parsing tasks with in-context learning. In the ID settings, the demonstrations are from the same split (test or train) that the model is being evaluated on, and in the OOD settings, they are from the other split. We look at how the relative generalization gap of in-context learning evolves as models are scaled up. We evaluate four model families, OPT, BLOOM, CodeGen and Codex on three semantic parsing datasets, CFQ, SCAN and GeoQuery with different number of exemplars, and observe a trend of decreasing relative generalization gap as models are scaled up.

Semantic parsing is the task of producing structured meaning representations for natural language sentences. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic parsers struggle to generalize systematically, i.e. to handle examples that require recombining known knowledge in novel settings. In this work, we show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence. To this end we propose LAGr (Label Aligned Graphs), a general framework to produce semantic parses by independently predicting node and edge labels for a complete multi-layer input-aligned graph. The strongly-supervised LAGr algorithm requires aligned graphs as inputs, whereas weakly-supervised LAGr infers alignments for originally unaligned target graphs using approximate maximum-a-posteriori inference. Experiments demonstrate that LAGr achieves significant improvements in systematic generalization upon the baseline seq2seq parsers in both strongly- and weakly-supervised settings.

Compositionality— the ability to combine familiar units like words into novel phrases and sentences— has been the focus of intense interest in artificial intelligence in recent years. To test compositional generalization in semantic parsing, Keysers et al. (2020) introduced Compositional Freebase Queries (CFQ). This dataset maximizes the similarity between the test and train distributions over primitive units, like words, while maximizing the compound divergence: the dissimilarity between test and train distributions over larger structures, like phrases. Dependency parsing, however, lacks a compositional generalization benchmark. In this work, we introduce a gold-standard set of dependency parses for CFQ, and use this to analyze the behaviour of a state-of-the art dependency parser (Qi et al., 2020) on the CFQ dataset. We find that increasing compound divergence degrades dependency parsing performance, although not as dramatically as semantic parsing performance. Additionally, we find the performance of the dependency parser does not uniformly degrade relative to compound divergence, and the parser performs differently on different splits with the same compound divergence. We explore a number of hypotheses for what causes the non-uniform degradation in dependency parsing performance, and identify a number of syntactic structures that drive the dependency parser’s lower performance on the most challenging splits.

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus. By training BERT with the resulting combined objective we reduce the mean top 1 error rate to 4% on the negated LAMA dataset. We also see some improvements on the negated NLI benchmarks.

Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the problem. Contrary to this trend, in this paper we focus on simplifications. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.

Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challenging Spider and CoSQL text-to-SQL translation tasks, we show that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.

Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by recent work by Li et al., we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method that outperforms the previous state of the art on predicting more novel triples.