Prior work shows that program-aided reasoning, in which large language models (LLMs) are combined with programs written in programming languages such as Python, can significantly improve accuracy on various reasoning tasks. However, while accuracy is essential, it is also important for such reasoners to “know what they know”, which can be quantified through the calibration of the model. In this paper, we compare the calibration of Program Aided Language Models (PAL) and text-based Chain-of-thought (COT) prompting techniques over 5 datasets and 2 model types - LLaMA models and OpenAI models. Our results indicate that PAL leads to improved calibration in 75% of the instances. Our analysis uncovers that prompting styles that produce lesser diversity in generations also have more calibrated results, and thus we also experiment with inducing lower generation diversity using temperature scaling and find that for certain temperatures, PAL is not only more accurate but is also more calibrated than COT. Overall, we demonstrate that, in the majority of cases, program-aided reasoners better know what they know than text-based counterparts.

Teaching machines to reason over texts has been a long-standing goal of natural language processing (NLP). To this end, researchers have designed a diverse set of complex reasoning tasks that involve compositional reasoning, knowledge retrieval, grounding, commonsense reasoning, etc. A standard choice for building systems that perform a desired type of reasoning is to fine-tune a pretrained language model (LM) on specific downstream tasks. However, recent research has demonstrated that such a straightforward approach is often brittle. For example, Elazar et al. (2021) and Branco et al. (2021) show that, on question-answering (QA) tasks, similar performance can be achieved with questions removed from the inputs. Min et al. (2019), Chen and Durrett (2019), and Tang et al. (2021) show that models trained on multi-hop QA do not generalize to answer single-hop questions. The reasoning capabilities of these models thus remain at a surface level, i.e., exploiting data patterns. Consequently, augmenting LMs with techniques that make them robust and effective becomes an active research area. We will start the tutorial by providing an overview of complex reasoning tasks where the standard application of pretrained language models fails. This tutorial then reviews recent promising directions for tackling these tasks. Specifically, we focus on the following groups of approaches that explicitly consider problem structures: (1) knowledge-augmented methods, where the knowledge is either incorporated during fine-tuning or pretraining; (2) few-shot prompting methods, which effectively guide the models to follow instructions; (3) neuro-symbolic methods, which produce explicit intermediate representations; and, (4) rationale-based methods, one of the most popular forms of the neuro-symbolic methods, which highlight subsets of input as explanations for individual model predictions.

The effectiveness of Chain-of-thought prompting (CoT) has been widely recognized, but the underlying mechanisms behind its success, the reason why it just works for a wide range of tasks, remains an open question. To investigate this, we employ a counterfactual prompting approach, systematically manipulating elements of examples used in a few-shot prompt, and testing the consequences on model behavior. This allows us to understand the relative contributions of prompt elements such as symbols (digits, entities) and patterns (equations, sentence structure) on in-context learning. Our experiments with three different large language models (LLMs) reveal several key findings. First, the specific symbols used in the prompt do not significantly impact the model’s performance. However, consistent patterns in examples and specifying text in style frequently found on the web are crucial. Second, our findings suggest that the necessity of accurate few-shot examples depends on their role in communicating task understanding. We identify tasks where inaccurate few-shot examples hurt and, surprisingly, tasks where they improve performance. Additionally, we find that the intermediate steps in CoT may not necessarily facilitate learning how to solve a task, but instead efficiently convey task understanding (what) to the model. Furthermore, CoT leverages LLMs to fill in missing commonsense information, particularly helping difficult reasoning problems and long-tail questions.

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a constant number of samples per question, where a better approach will be to non-uniformly distribute the available budget based on the amount of agreement in the samples generated so far. In response, we introduce Adaptive-Consistency, a cost-efficient, model-agnostic technique that dynamically adjusts the number of samples per question using a lightweight stopping criterion. Our experiments over 17 reasoning and code generation datasets and three LLMs demonstrate that Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%

Natural language generation has witnessed significant advancements due to the training of large language models on vast internet-scale datasets. Despite these advancements, there exists a critical challenge: These models can inadvertently generate content that is toxic, inaccurate, and unhelpful, and existing automatic evaluation metrics often fall short of identifying these shortcomings. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of recent research that has leveraged human feedback to improve natural language generation. First, we introduce a taxonomy distilled from existing research to categorize and organize the varied forms of feedback. Next, we discuss how feedback can be described by its format and objective, and cover the two approaches proposed to use feedback (either for training or decoding): directly using feedback or training feedback models. We also discuss existing datasets for human-feedback data collection, and concerns surrounding feedback collection. Finally, we provide an overview of the nascent field of AI feedback, which uses large language models to make judgments based on a set of principles and minimize the need for human intervention. We also release a website of this survey at feedback-gap-survey.info.

We address the general task of structured commonsense reasoning: given a natural language input, the goal is to generate a graph such as an event or a reasoning-graph.To employ large language models (LMs) for this task, existing approaches ‘serialize’ the output graph as a flat list of nodes and edges.Although feasible, these serialized graphs strongly deviate from the natural language corpora that LMs were pre-trained on, hindering LMs from generating them correctly. In this paper, we show that when we instead frame structured commonsense reasoning tasks as code generation tasks, pre-trained LMs of code are better structured commonsense reasoners than LMs of natural language, even when the downstream task does not involve source code at all.We demonstrate our approach across three diverse structured commonsense reasoning tasks. In all these natural language tasks, we show that using our approach, a code generation LM (codex) outperforms natural-LMs that are fine-tuned on the target task (T5) and other strong LMs such as GPT-3 in the few-shot setting.

Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret “What word is similar to good?” to mean a homophone, while the user intended a synonym. Our goal is to effectively correct such errors via user interactions with the system but without retraining, which will be prohibitively costly. We pair GPT-3 with a growing memory of recorded cases where the model misunderstood the user’s intents, along with user feedback for clarification. Such a memory allows our system to produce enhanced prompts for any new query based on the user feedback for error correction on similar cases in the past. On four tasks (two lexical tasks, two advanced ethical reasoning tasks), we show how a (simulated) user can interactively teach a deployed GPT-3, substantially increasing its accuracy over the queries with different kinds of misunderstandings by the GPT-3. Our approach is a step towards the low-cost utility enhancement for very large pre-trained LMs.

Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models are a popular choice to model set generation but they treat a set as a sequence and do not fully leverage its key properties, namely order-invariance and cardinality. We propose a novel algorithm for effectively sampling informative orders over the combinatorial space of label orders. Further, we jointly model the set cardinality and output by listing the set size as the first element and taking advantage of the autoregressive factorization used by Seq2Seq models. Our method is a model-independent data augmentation approach that endows any Seq2Seq model with the signals of order-invariance and cardinality. Training a Seq2Seq model on this new augmented data (without any additional annotations), gets an average relative improvement of 20% for four benchmarks datasets across models spanning from BART-base, T5-11B, and GPT-3. We will release all code and data upon acceptance.

Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods and what should be standardized instead is how to incorporate these new evaluation advances. We introduce GEMv2, the new version of the Generation, Evaluation, and Metrics Benchmark which uses a modular infrastructure for dataset, model, and metric developers to benefit from each other’s work. GEMv2 supports 40 documented datasets in 51 languages, ongoing online evaluation for all datasets, and our interactive tools make it easier to add new datasets to the living benchmark.

Large language models (LMs), while powerful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user. Our approach pairs an LM with (i) a growing memory of cases where the user identified an output error and provided general feedback on how to correct it (ii) a corrector model, trained to translate this general feedback into specific edits to repair the model output. Given a new, unseen input, our model can then use feedback from similar, past cases to repair output errors that may occur. We instantiate our approach using an existing, fixed model for script generation, that takes a goal (e.g., “bake a cake”) and generates a partially ordered sequence of actions to achieve that goal, sometimes containing errors. Our memory-enhanced system, , learns to apply user feedback to repair such errors (up to 30 points improvement), while making a start at avoiding similar past mistakes on new, unseen examples (up to 7 points improvement in a controlled setting). This is a first step towards strengthening deployed models, potentially broadening their utility. Our code and data is available at https://github.com/allenai/interscript

Predicting the effects of unexpected situations is an important reasoning task, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situational reasoning is to elicit the consequences of a new situation (st) that arises in that context. We propose CURIE, a method to iteratively build a graph of relevant consequences explicitly in a structured situational graph (st graph) using natural language queries over a finetuned language model. Across multiple domains, CURIE generates st graphs that humans find relevant and meaningful in eliciting the consequences of a new situation (75% of the graphs were judged correct by humans). We present a case study of a situation reasoning end task (WIQA-QA), where simply augmenting their input with st graphs improves accuracy by 3 points. We show that these improvements mainly come from a hard subset of the data, that requires background knowledge and multi-hop reasoning.

This paper presents the first study on using large-scale pre-trained language models for automated generation of an event-level temporal graph for a document. Despite the huge success of neural pre-training methods in NLP tasks, its potential for temporal reasoning over event graphs has not been sufficiently explored. Part of the reason is the difficulty in obtaining large training corpora with human-annotated events and temporal links. We address this challenge by using existing IE/NLP tools to automatically generate a large quantity (89,000) of system-produced document-graph pairs, and propose a novel formulation of the contextualized graph generation problem as a sequence-to-sequence mapping task. These strategies enable us to leverage and fine-tune pre-trained language models on the system-induced training data for the graph generation task. Our experiments show that our approach is highly effective in generating structurally and semantically valid graphs. Further, evaluation on a challenging hand-labeled, out-of-domain corpus shows that our method outperforms the closest existing method by a large margin on several metrics. We also show a downstream application of our approach by adapting it to answer open-ended temporal questions in a reading comprehension setting.

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for the 2021 shared task at the associated GEM Workshop.

Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning suggests that a person forms a “mental model” of the problem scenario before answering questions. Our research goal asks whether neural models can similarly benefit from envisioning the question scenario before answering a defeasible query. Our approach is, given a question, to have a model first create a graph of relevant influences, and then leverage that graph as an additional input when answering the question. Our system, CURIOUS, achieves a new state-of-the-art on three different defeasible reasoning datasets. This result is significant as it illustrates that performance can be improved by guiding a system to “think about” a question and explicitly model the scenario, rather than answering reflexively.

This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning. We also provide a dataset of more than 1.39 instances automatically labeled for politeness to encourage benchmark evaluations on this new task. We design a tag and generate pipeline that identifies stylistic attributes and subsequently generates a sentence in the target style while preserving most of the source content. For politeness as well as five other transfer tasks, our model outperforms the state-of-the-art methods on automatic metrics for content preservation, with a comparable or better performance on style transfer accuracy. Additionally, our model surpasses existing methods on human evaluations for grammaticality, meaning preservation and transfer accuracy across all the six style transfer tasks. The data and code is located at https://github.com/tag-and-generate.