The impressive generation capabilities of large language models (LLMs) have made it harder to detect the subtle hallucinations they make in abstractive summarization, where generated summaries consist of a blend of correct and incorrect information w.r.t. a given document. Recently-proposed LLM-based evaluation metrics attempt to capture this, but still face challenges: (1) they are biased towards summaries generated from the same underlying LLM, and (2) they lack interpretability, offering only a single score. In this work, we present ACUEval, a metric that leverages the power of LLMs to perform two sub-tasks: decomposing summaries into atomic content units (ACUs), and validating them against the source document. Compared to current strong LLM-based metrics, our two-step evaluation strategy improves correlation with human judgments of faithfulness on three summarization evaluation benchmarks by 3% in balanced accuracy compared to the next-best metric, and also shows reduced preference bias towards LLM-generated summary. Further, we show that errors detected by ACUEval can be used to generate actionable feedback for refining the summary, improving the faithfulness scores by more than 10%.

Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations and self-improve?A popular concept, referred to as *self-refinement*, postulates that LLMs can detect and correct the errors in their generations when asked to do so. However, recent empirical evidence points in the opposite direction, suggesting that LLMs often struggle to accurately identify errors when reasoning is involved. To address this, we propose a reasoning with a refinement strategy called *ART: Ask, Refine, and Trust*, which *asks* necessary questions to decide when an LLM should *refine* its output, and uses it to affirm or deny *trust* in its refinement by ranking the refinement and the initial prediction. On two multistep reasoning tasks of mathematical word problems (GSM8K) and question answering (StrategyQA), *ART* achieves a performance gain of +5 points over self-refinement baselines, while using a much smaller model as the decision maker. We believe that *ART* with smaller models, making refinement decisions can be a cost-effective alternative to fine-tuning LLMs.

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Our best syntactic evaluation datasets, however, provide substantially less linguistic context than models receive during pretraining. This mismatch raises an important question: how robust are models’ syntactic judgements across different contexts? In this paper, we vary the input contexts based on: length, the types of syntactic phenomena it contains, and whether or not there are grammatical violations. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts, but are unstable when contexts match the test stimuli in syntactic structure. Among all tested models (GPT-2 and five variants of OPT), we find that model performance is affected when we provided contexts with matching syntactic structure: performance significantly improves when contexts are acceptable, and it significantly declines when they are unacceptable. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by acceptability-preserving syntactic perturbations. This sensitivity to highly specific syntactic features of the context can only be explained by the models’ implicit in-context learning abilities.

A key feature of modern large language models (LLMs) is their ability to perform in-context learning, a prompting technique where query- answer demonstrations are shown before the final query. This allows for generalization to novel distributions at inference time where the LLM can learn new rules without parameter updates. However, the choice of demonstrations and their relationship to a particular query can have a profound impact on model accuracy, raising concerns about the true in-context generalization capabilities (Zhao et al., 2021). In this work, we explore the robustness of the in-context learning paradigm by focusing on entities. In particular, we seek to understand the robustness of LLM in-context learning with respect to named entity replacements. We discover a significant variance in downstream performance based on the choice of the named entities, across three popular reasoning tasks and two popular LLMs. Specifically, model accuracy on the test sets can fluctuate between -2.7 to +8.0 points depending on the choice of named entity replacements. Our analysis exposes the sensitivity of LLM in-context learning with respect to named entities, and offers a simple recipe to improve test performance by hyper-parameter tuning the named entities for a given dataset. Code and datasets for reproducing the results are publicly available.

While recent progress in the field of ML has been significant, the reproducibility of these cutting-edge results is often lacking, with many submissions lacking the necessary information in order to ensure subsequent reproducibility. Despite proposals such as the Reproducibility Checklist and reproducibility criteria at several major conferences, the reflex for carrying out research with reproducibility in mind is lacking in the broader ML community. We propose this tutorial as a gentle introduction to ensuring reproducible research in ML, with a specific emphasis on computational linguistics and NLP. We also provide a framework for using reproducibility as a teaching tool in university-level computer science programs.

Neural Machine Translation systems built on top of Transformer-based architectures are routinely improving the state-of-the-art in translation quality according to word-overlap metrics. However, a growing number of studies also highlight the inherent gender bias that these models incorporate during training, which reflects poorly in their translations. In this work, we investigate whether these models can be instructed to fix their bias during inference using targeted, guided instructions as contexts. By translating relevant contextual sentences during inference along with the input, we observe large improvements in reducing the gender bias in translations, across three popular test suites (WinoMT, BUG, SimpleGen). We further propose a novel metric to assess several large pre-trained models (OPUS-MT, M2M-100) on their sensitivity towards using contexts during translation to correct their biases. Our approach requires no fine-tuning, and thus can be used easily in production systems to de-bias translations from stereotypical gender-occupation bias. We hope our method, along with our metric, can be used to build better, bias-free translation systems.

Transformer language models encode the notion of word order using positional information. Most commonly, this positional information is represented by absolute position embeddings (APEs), that are learned from the pretraining data. However, in natural language, it is not absolute position that matters, but relative position, and the extent to which APEs can capture this type of information has not been studied. In this work, we observe that models trained with APE over-rely on positional information to the point that they break-down when subjected to sentences with shifted position information. Specifically, when models are subjected to sentences starting from a non-zero position (excluding the effect of priming), they exhibit noticeably degraded performance on zero- to full-shot tasks, across a range of model families and model sizes. Our findings raise questions about the efficacy of APEs to model the relativity of position information, and invite further introspection on the sentence and word order processing strategies employed by these models.

Recent investigations into the inner-workings of state-of-the-art large-scale pre-trained Transformer-based Natural Language Understanding (NLU) models indicate that they appear to understand human-like syntax, at least to some extent. We provide novel evidence that complicates this claim: we find that state-of-the-art Natural Language Inference (NLI) models assign the same labels to permuted examples as they do to the original, i.e. they are invariant to random word-order permutations. This behavior notably differs from that of humans; we struggle to understand the meaning of ungrammatical sentences. To measure the severity of this issue, we propose a suite of metrics and investigate which properties of particular permutations lead models to be word order invariant. For example, in MNLI dataset we find almost all (98.7%) examples contain at least one permutation which elicits the gold label. Models are even able to assign gold labels to permutations that they originally failed to predict correctly. We provide a comprehensive empirical evaluation of this phenomenon, and further show that this issue exists in pre-Transformer RNN / ConvNet based encoders, as well as across multiple languages (English and Chinese). Our code and data are available at https://github.com/facebookresearch/unlu.

Rapid progress in Neural Machine Translation (NMT) systems over the last few years has focused primarily on improving translation quality, and as a secondary focus, improving robustness to perturbations (e.g. spelling). While performance and robustness are important objectives, by over-focusing on these, we risk overlooking other important properties. In this paper, we draw attention to the fact that for some applications, faithfulness to the original (input) text is important to preserve, even if it means introducing unusual language patterns in the (output) translation. We propose a simple, novel way to quantify whether an NMT system exhibits robustness or faithfulness, by focusing on the case of word-order perturbations. We explore a suite of functions to perturb the word order of source sentences without deleting or injecting tokens, and measure their effects on the target side. Across several experimental conditions, we observe a strong tendency towards robustness rather than faithfulness. These results allow us to better understand the trade-off between faithfulness and robustness in NMT, and opens up the possibility of developing systems where users have more autonomy and control in selecting which property is best suited for their use case.

A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a different explanation: MLMs succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. To demonstrate this, we pre-train MLMs on sentences with randomly shuffled word order, and show that these models still achieve high accuracy after fine-tuning on many downstream tasks—including tasks specifically designed to be challenging for models that ignore word order. Our models perform surprisingly well according to some parametric syntactic probes, indicating possible deficiencies in how we test representations for syntactic information. Overall, our results show that purely distributional information largely explains the success of pre-training, and underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.

Recently, there has been much interest in the question of whether deep natural language understanding (NLU) models exhibit systematicity, generalizing such that units like words make consistent contributions to the meaning of the sentences in which they appear. There is accumulating evidence that neural models do not learn systematically. We examine the notion of systematicity from a linguistic perspective, defining a set of probing tasks and a set of metrics to measure systematic behaviour. We also identify ways in which network architectures can generalize non-systematically, and discuss why such forms of generalization may be unsatisfying. As a case study, we perform a series of experiments in the setting of natural language inference (NLI). We provide evidence that current state-of-the-art NLU systems do not generalize systematically, despite overall high performance.

Evaluating the quality of a dialogue interaction between two agents is a difficult task, especially in open-domain chit-chat style dialogue. There have been recent efforts to develop automatic dialogue evaluation metrics, but most of them do not generalize to unseen datasets and/or need a human-generated reference response during inference, making it infeasible for online evaluation. Here, we propose an unreferenced automated evaluation metric that uses large pre-trained language models to extract latent representations of utterances, and leverages the temporal transitions that exist between them. We show that our model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference.

The recent success of natural language understanding (NLU) systems has been troubled by results highlighting the failure of these models to generalize in a systematic and robust way. In this work, we introduce a diagnostic benchmark suite, named CLUTRR, to clarify some key issues related to the robustness and systematicity of NLU systems. Motivated by the classic work on inductive logic programming, CLUTRR requires that an NLU system infer kinship relations between characters in short stories. Successful performance on this task requires both extracting relationships between entities, as well as inferring the logical rules governing these relationships. CLUTRR allows us to precisely measure a model’s ability for systematic generalization by evaluating on held-out combinations of logical rules, and allows us to evaluate a model’s robustness by adding curated noise facts. Our empirical results highlight a substantial performance gap between state-of-the-art NLU models (e.g., BERT and MAC) and a graph neural network model that works directly with symbolic inputs—with the graph-based model exhibiting both stronger generalization and greater robustness.

Deep neural networks have been displaying superior performance over traditional supervised classifiers in text classification. They learn to extract useful features automatically when sufficient amount of data is presented. However, along with the growth in the number of documents comes the increase in the number of categories, which often results in poor performance of the multiclass classifiers. In this work, we use external knowledge in the form of topic category taxonomies to aide the classification by introducing a deep hierarchical neural attention-based classifier. Our model performs better than or comparable to state-of-the-art hierarchical models at significantly lower computational cost while maintaining high interpretability.