We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting. To this end, we create MACGYVER, an automatically generated dataset consisting of over 1,600 real-world problems deliberately designed to trigger innovative usage of objects and necessitate out-of-the-box thinking. We then present our collection to both LLMs and humans to compare and contrast their problem-solving abilities. MACGYVER is challenging for both groups, but in unique and complementary ways. For instance, humans excel in tasks they are familiar with but struggle with domain-specific knowledge, leading to a higher variance. In contrast, LLMs, exposed to a variety of specialized knowledge, attempt broader problems but fail by proposing physically-infeasible actions. Finally, we provide a detailed error analysis of LLMs, and demonstrate the potential of enhancing their problem-solving ability with novel prompting techniques such as iterative step-wise reflection and divergent-convergent thinking.This work (1) introduces a fresh arena for intelligent agents focusing on intricate aspects of physical reasoning, planning, and unconventional thinking, which supplements the existing spectrum of machine intelligence; and (2) provides insight into the constrained problem-solving capabilities of both humans and AI.

Multiple-choice question answering (MCQA) is often used to evaluate large language models (LLMs). To see if MCQA assesses LLMs as intended, we probe if LLMs can perform MCQA with choices-only prompts, where models must select the correct answer only from the choices. In three MCQA datasets and four LLMs, this prompt bests a majority baseline in 11/12 cases, with up to 0.33 accuracy gain. To help explain this behavior, we conduct an in-depth, black-box analysis on memorization, choice dynamics, and question inference. Our key findings are threefold. First, we find no evidence that the choices-only accuracy stems from memorization alone. Second, priors over individual choices do not fully explain choices-only accuracy, hinting that LLMs use the group dynamics of choices. Third, LLMs have some ability to infer a relevant question from choices, and surprisingly can sometimes even match the original question. We hope to motivate the use of stronger baselines in MCQA benchmarks, the design of robust MCQA datasets, and further efforts to explain LLM decision-making.

Closed-source agents suffer from several issues such as a lack of affordability, transparency, and reproducibility, particularly on complex interactive tasks. This motivates the development of open-source alternatives. We introduce Lumos, one of the first frameworks for training open-source LLM-based agents. Lumos features a learnable, unified and modular architecture with a planning module that learns high-level subgoal generation, and a grounding module trained to translate these into the actions using various tools in the execution module. The design allows for modular upgrades and wider applicability to diverse interactive tasks. To foster generalizable agent learning, we collect large-scale, unified, and high-quality training annotations derived from diverse ground-truth reasoning rationales across various complex interactive tasks. On 9 datasets, Lumos exhibits several key advantages: (1) Lumos excels multiple larger open-source agents on the held-out datasets (unused for training) for each task type. Lumos even surpasses GPT agents on QA and web tasks; (2) Lumos outperforms open-source agents produced by chain-of-thoughts and unmodularized integrated training; and (3) Lumos effectively generalizes to unseen tasks, outperforming 33B-scale agents and domain-specific agents. Code and data will be released.

Information about pretraining corpora used to train the current best-performing language models is seldom discussed: commercial models rarely detail their data, and even open models are often released without accompanying training data or recipes to reproduce them. As a result, it is challenging to conduct and advance scientific research on language modeling, such as understanding how training data impacts model capabilities and limitations. To facilitate scientific research on language model pretraining, we curate and release Dolma, a three-trillion-token English corpus, built from a diverse mixture of web content, scientific papers, code, public-domain books, social media, and encyclopedic materials. We extensively document Dolma, including its design principles, details about its construction, and a summary of its contents. We present analyses and experimental results on intermediate states of Dolma to share what we have learned about important data curation practices. Finally, we open-source our data curation toolkit to enable reproduction of our work as well as support further research in large-scale data curation.

Language models (LMs) have become ubiquitous in both NLP research and in commercial product offerings. As their commercial importance has surged, the most powerful models have become closed off, gated behind proprietary interfaces, with important details of their training data, architectures, and development undisclosed. Given the importance of these details in scientifically studying these models, including their biases and potential risks, we believe it is essential for the research community to have access to powerful, truly open LMs. To this end, we have built OLMo, a competitive, truly Open Language Model, to enable the scientific study of language models. Unlike most prior efforts that have only released model weights and inference code, we release OLMo alongside open training data and training and evaluation code. We hope this release will empower the open research community and inspire a new wave of innovation.

Neural models have been shown to exploit shallow surface features to perform language understanding tasks, rather than learning the deeper language understanding and reasoning skills that practitioners desire. Previous work has developed debiasing techniques to pressure models away from spurious features or artifacts in datasets, with the goal of having models instead learn useful, task-relevant representations. However, what do models actually learn as a result of such debiasing procedures? In this work, we evaluate three model debiasing strategies, and through a set of carefully designed tests we show how debiasing can actually increase the model’s reliance on hidden biases, instead of learning robust features that help it solve a task. Further, we demonstrate how even debiasing models against all shallow features in a dataset may still not help models address NLP tasks. As a result, we suggest that debiasing existing models may not be sufficient for many language understanding tasks, and future work should consider new learning paradigms, to address complex challenges such as commonsense reasoning and inference.

While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited. Directly fine-tuning such language models can be effective for tailoring them, but it can be either extremely costly (e.g., GPT-3) or not even feasible for the broader community (e.g., GPT-4). We propose Inference-time Policy Adapters (IPA), which efficiently tailors a language model such as GPT-3 without fine-tuning it. IPA guides a large base model during decoding time through a lightweight policy adapter trained to optimize an arbitrary user objective with reinforcement learning. On five challenging text generation tasks, such as toxicity reduction and lexically constrained generation, IPA consistently brings significant improvements over off-the-shelf language models. It outperforms competitive baseline methods, sometimes even including expensive fine-tuning. In particular, tailoring GPT-2 with IPA can outperform GPT-3, while tailoring GPT-3 with IPA brings a major performance boost over GPT-3 (and sometimes even over GPT-4). Our promising results highlight the potential of IPA as a lightweight alternative to tailoring extreme-scale language models.

The full power of human language-based communication cannot be realized without negation. All human languages have some form of negation. Despite this, negation remains a challenging phenomenon for current natural language understanding systems. To facilitate the future development of models that can process negation effectively, we present CONDAQA, the first English reading comprehension dataset which requires reasoning about the implications of negated statements in paragraphs. We collect paragraphs with diverse negation cues, then have crowdworkers ask questions about the implications of the negated statement in the passage. We also have workers make three kinds of edits to the passage—paraphrasing the negated statement, changing the scope of the negation, and reversing the negation—resulting in clusters of question-answer pairs that are difficult for models to answer with spurious shortcuts. CONDAQA features 14,182 question-answer pairs with over 200 unique negation cues and is challenging for current state-of-the-art models. The best performing model on CONDAQA (UnifiedQA-v2-3b) achieves only 42% on our consistency metric, well below human performance which is 81%. We release our dataset, along with fully-finetuned, few-shot, and zero-shot evaluations, to facilitate the development of future NLP methods that work on negated language.

Over the past decade, researchers have started to explore the use of NLP to develop tools aimed at helping the public, vendors, and regulators analyze disclosures made in privacy policies. With the introduction of new privacy regulations, the language of privacy policies is also evolving, and disclosures made by the same organization are not always the same in different languages, especially when used to communicate with users who fall under different jurisdictions. This work explores the use of language technologies to capture and analyze these differences at scale. We introduce an annotation scheme designed to capture the nuances of two new landmark privacy regulations, namely the EU’s GDPR and California’s CCPA/CPRA. We then introduce the first bilingual corpus of mobile app privacy policies consisting of 64 privacy policies in English (292K words) and 91 privacy policies in German (478K words), respectively with manual annotations for 8K and 19K fine-grained data practices. The annotations are used to develop computational methods that can automatically extract “disclosures” from privacy policies. Analysis of a subset of 59 “semi-parallel” policies reveals differences that can be attributed to different regulatory regimes, suggesting that systematic analysis of policies using automated language technologies is indeed a worthwhile endeavor.

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.

Privacy plays a crucial role in preserving democratic ideals and personal autonomy. The dominant legal approach to privacy in many jurisdictions is the “Notice and Choice” paradigm, where privacy policies are the primary instrument used to convey information to users. However, privacy policies are long and complex documents that are difficult for users to read and comprehend. We discuss how language technologies can play an important role in addressing this information gap, reporting on initial progress towards helping three specific categories of stakeholders take advantage of digital privacy policies: consumers, enterprises, and regulators. Our goal is to provide a roadmap for the development and use of language technologies to empower users to reclaim control over their privacy, limit privacy harms, and rally research efforts from the community towards addressing an issue with large social impact. We highlight many remaining opportunities to develop language technologies that are more precise or nuanced in the way in which they use the text of privacy policies.

Consistency of a model—that is, the invariance of its behavior under meaning-preserving alternations in its input—is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge? To this end, we create ParaRel🤘, a high-quality resource of cloze-style query English paraphrases. It contains a total of 328 paraphrases for 38 relations. Using ParaRel🤘, we show that the consistency of all PLMs we experiment with is poor— though with high variance between relations. Our analysis of the representational spaces of PLMs suggests that they have a poor structure and are currently not suitable for representing knowledge robustly. Finally, we propose a method for improving model consistency and experimentally demonstrate its effectiveness.1

During production of this paper, an error was introduced to the formula on the bottom of the right column of page 1020. In the last two terms of the formula, the n and m subscripts were swapped. The correct formula is:Lc=∑n=1k∑m=n+1kDKL(Qnri∥Qmri)+DKL(Qmri∥Qnri)The paper has been updated.

When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into a search engine, or even translating questions to languages supported by the QA system. While there has been significant community attention devoted to identifying correct answers in passages assuming a perfectly formed question, we show that components in the pipeline that precede an answering engine can introduce varied and considerable sources of error, and performance can degrade substantially based on these upstream noise sources even for powerful pre-trained QA models. We conclude that there is substantial room for progress before QA systems can be effectively deployed, highlight the need for QA evaluation to expand to consider real-world use, and hope that our findings will spur greater community interest in the issues that arise when our systems actually need to be of utility to humans.

Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks. Thus, much recent attention has been devoted to analyzing the sentence representations learned by neural encoders, through the lens of ‘probing’ tasks. However, to what extent was the information encoded in sentence representations, as discovered through a probe, actually used by the model to perform its task? In this work, we examine this probing paradigm through a case study in Natural Language Inference, showing that models can learn to encode linguistic properties even if they are not needed for the task on which the model was trained. We further identify that pretrained word embeddings play a considerable role in encoding these properties rather than the training task itself, highlighting the importance of careful controls when designing probing experiments. Finally, through a set of controlled synthetic tasks, we demonstrate models can encode these properties considerably above chance-level, even when distributed in the data as random noise, calling into question the interpretation of absolute claims on probing tasks.

Contextualized word representations have become a driving force in NLP, motivating widespread interest in understanding their capabilities and the mechanisms by which they operate. Particularly intriguing is their ability to identify and encode conceptual abstractions. Past work has probed BERT representations for this competence, finding that BERT can correctly retrieve noun hypernyms in cloze tasks. In this work, we ask the question: do probing studies shed light on systematic knowledge in BERT representations? As a case study, we examine hypernymy knowledge encoded in BERT representations. In particular, we demonstrate through a simple consistency probe that the ability to correctly retrieve hypernyms in cloze tasks, as used in prior work, does not correspond to systematic knowledge in BERT. Our main conclusion is cautionary: even if BERT demonstrates high probing accuracy for a particular competence, it does not necessarily follow that BERT ‘understands’ a concept, and it cannot be expected to systematically generalize across applicable contexts.

We present the results of three Shared Tasks held at the Scholarly Document Processing Workshop at EMNLP2020: CL-SciSumm, LaySumm and LongSumm. We report on each of the tasks, which received 18 submissions in total, with some submissions addressing two or three of the tasks. In summary, the quality and quantity of the submissions show that there is ample interest in scholarly document summarization, and the state of the art in this domain is at a midway point between being an impossible task and one that is fully resolved.

Word embeddings are now pervasive across NLP subfields as the de-facto method of forming text representataions. In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of mathematical meaning for numbers, which is important for language understanding. Numbers are ubiquitous and frequently appear in text. Inspired by cognitive studies on how humans perceive numbers, we develop an analysis framework to test how well word embeddings capture two essential properties of numbers: magnitude (e.g. 3<4) and numeration (e.g. 3=three). Our experiments reveal that most models capture an approximate notion of magnitude, but are inadequate at capturing numeration. We hope that our observations provide a starting point for the development of methods which better capture numeracy in NLP systems.

Quantitative reasoning is a higher-order reasoning skill that any intelligent natural language understanding system can reasonably be expected to handle. We present EQUATE (Evaluating Quantitative Understanding Aptitude in Textual Entailment), a new framework for quantitative reasoning in textual entailment. We benchmark the performance of 9 published NLI models on EQUATE, and find that on average, state-of-the-art methods do not achieve an absolute improvement over a majority-class baseline, suggesting that they do not implicitly learn to reason with quantities. We establish a new baseline Q-REAS that manipulates quantities symbolically. In comparison to the best performing NLI model, it achieves success on numerical reasoning tests (+24.2 %), but has limited verbal reasoning capabilities (-8.1 %). We hope our evaluation framework will support the development of models of quantitative reasoning in language understanding.

Privacy policies are long and complex documents that are difficult for users to read and understand. Yet, they have legal effects on how user data can be collected, managed and used. Ideally, we would like to empower users to inform themselves about the issues that matter to them, and enable them to selectively explore these issues. We present PrivacyQA, a corpus consisting of 1750 questions about the privacy policies of mobile applications, and over 3500 expert annotations of relevant answers. We observe that a strong neural baseline underperforms human performance by almost 0.3 F1 on PrivacyQA, suggesting considerable room for improvement for future systems. Further, we use this dataset to categorically identify challenges to question answerability, with domain-general implications for any question answering system. The PrivacyQA corpus offers a challenging corpus for question answering, with genuine real world utility.

Natural language inference (NLI) is the task of determining if a natural language hypothesis can be inferred from a given premise in a justifiable manner. NLI was proposed as a benchmark task for natural language understanding. Existing models perform well at standard datasets for NLI, achieving impressive results across different genres of text. However, the extent to which these models understand the semantic content of sentences is unclear. In this work, we propose an evaluation methodology consisting of automatically constructed “stress tests” that allow us to examine whether systems have the ability to make real inferential decisions. Our evaluation of six sentence-encoder models on these stress tests reveals strengths and weaknesses of these models with respect to challenging linguistic phenomena, and suggests important directions for future work in this area.

Self-disclosure is a key social strategy employed in conversation to build relations and increase conversational depth. It has been heavily studied in psychology and linguistic literature, particularly for its ability to induce self-disclosure from the recipient, a phenomena known as reciprocity. However, we know little about how self-disclosure manifests in conversation with automated dialog systems, especially as any self-disclosure on the part of a dialog system is patently disingenuous. In this work, we run a large-scale quantitative analysis on the effect of self-disclosure by analyzing interactions between real-world users and a spoken dialog system in the context of social conversation. We find that indicators of reciprocity occur even in human-machine dialog, with far-reaching implications for chatbots in a variety of domains including education, negotiation and social dialog.

We investigate the pertinence of methods from algebraic topology for text data analysis. These methods enable the development of mathematically-principled isometric-invariant mappings from a set of vectors to a document embedding, which is stable with respect to the geometry of the document in the selected metric space. In this work, we evaluate the utility of these topology-based document representations in traditional NLP tasks, specifically document clustering and sentiment classification. We find that the embeddings do not benefit text analysis. In fact, performance is worse than simple techniques like tf-idf, indicating that the geometry of the document does not provide enough variability for classification on the basis of topic or sentiment in the chosen datasets.

Building dialogue interfaces for real-world scenarios often entails training semantic parsers starting from zero examples. How can we build datasets that better capture the variety of ways users might phrase their queries, and what queries are actually realistic? Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording. A limitation of this approach is that it induces bias towards using similar language as the canonical utterances. In this work, we present a methodology that elicits meaningful and lexically diverse queries from users for semantic parsing tasks. Starting from a seed lexicon and a generative grammar, we pair logical forms with mixed text-image representations and ask crowdworkers to paraphrase and confirm the plausibility of the queries that they generated. We use this method to build a semantic parsing dataset from scratch for a dialog agent in a smart-home simulation. We find evidence that this dataset, which we have named SmartHome, is demonstrably more lexically diverse and difficult to parse than existing domain-specific semantic parsing datasets.