How-to procedures, such as how to plant a garden, are now used by millions of users, but sometimes need customizing to meet a user’s specific needs, e.g., planting a garden without pesticides. Our goal is to measure and improve an LLM’s ability to perform such customization. Our approach is to test several simple multi-LLM-agent architectures for customization, as well as an end-to-end LLM, using a new evaluation set, called CustomPlans, of over 200 WikiHow procedures each with a customization need. We find that a simple architecture with two LLM agents used sequentially performs best, one that edits a generic how-to procedure and one that verifies its executability, significantly outperforming (10.5% absolute) an end-to-end prompted LLM. This suggests that LLMs can be configured reasonably effectively for procedure customization. This also suggests that multi-agent editing architectures may be worth exploring further for other customization applications (e.g. coding, creative writing) in the future.

Planning in textual environments have been shown to be a long-standing challenge even for current models. A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner. However, existing methods rely on a fully-observed environment where all entity states are initially known, so a one-off representation can be constructed, leading to a complete plan. In contrast, we tackle partially-observed environments where there is initially no sufficient information to plan for the end-goal. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. By accomplishing the sub-goal, more information is acquired to augment the representation, eventually achieving the end-goal. We show that plans produced by few-shot PDDLEGO are 43% more efficient than generating plans end-to-end on the Coin Collector simulation, with strong performance (98%) on the more complex Cooking World simulation where end-to-end LLMs fail to generate coherent plans (4%).

Planning in a text-based environment continues to be a significant challenge for AI systems. Recent approaches have utilized language models to predict planning domain definitions (e.g., PDDL) but have only been evaluated in closed-domain simulated environments. To address this, we present Proc2PDDL, the first dataset containing open-domain procedural texts paired with expert-annotated PDDL representations. Using this dataset, we evaluate the task of predicting domain actions (parameters, preconditions, and effects). We experiment with various large language models (LLMs) and prompting mechanisms, including a novel instruction inspired by the zone of proximal development (ZPD), which reconstructs the task as incremental basic skills. Our results demonstrate that Proc2PDDL is highly challenging for end-to-end LLMs, with GPT-3.5’s success rate close to 0% and GPT-4o’s 38%. With ZPD instructions, GPT-4o’s success rate increases to 45%, outperforming regular chain-of-thought prompting’s 34%. Our analysis systematically examines both syntactic and semantic errors, providing insights into the strengths and weaknesses of language models in generating domain-specific programs.

Much texts describe a changing world (e.g., procedures, stories, newswires), and understanding them requires tracking how entities change. An earlier dataset, OpenPI, provided crowdsourced annotations of entity state changes in text. However, a major limitation was that those annotations were free-form and did not identify salient changes, hampering model evaluation. To overcome these limitations, we present an improved dataset, OpenPI2.0, where entities and attributes are fully canonicalized and additional entity salience annotations are added. On our fairer evaluation setting, we find that current state-of-the-art language models are far from competent. We also show that using state changes of salient entities as a chain-of-thought prompt, downstream performance is improved on tasks such as question answering and classical planning, outperforming the setting involving all related entities indiscriminately. We offer OpenPI2.0 for the continued development of models that can understand the dynamics of entities in text.

The awareness of multi-cultural human values is critical to the ability of language models (LMs) to generate safe and personalized responses. However, this awareness of LMs has been insufficiently studied, since the computer science community lacks access to the large-scale real-world data about multi-cultural values. In this paper, we present WorldValuesBench, a globally diverse, large-scale benchmark dataset for the multi-cultural value prediction task, which requires a model to generate a rating response to a value question based on demographic contexts. Our dataset is derived from an influential social science project, World Values Survey (WVS), that has collected answers to hundreds of value questions (e.g., social, economic, ethical) from 94,728 participants worldwide. We have constructed more than 20 million examples of the type "(demographic attributes, value question) → answer” from the WVS responses. We perform a case study using our dataset and show that the task is challenging for strong open and closed-source models. On merely 11.1%, 25.0%, 72.2%, and 75.0% of the questions, Alpaca-7B, Vicuna-7B-v1.5, Mixtral-8x7B-Instruct-v0.1, and GPT-3.5 Turbo can respectively achieve <0.2 Wasserstein 1-distance from the human normalized answer distributions. WorldValuesBench opens up new research avenues in studying limitations and opportunities in multi-cultural value awareness of LMs.

Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training. However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer. Commonsense knowledge with multiple correct answers, e.g., an apple can be green or red but not transparent, has not been studied but is as essential for enhancing transformers’ reliability and usefulness. In this paper, we investigate whether commonsense judgments are causally associated with localized, editable parameters in Transformers, and we provide an affirmative answer. We find that directly applying the MEMIT editing algorithm results in sub-par performance and improve it for the commonsense domain by varying edit tokens and improving the layer selection strategy, i.e., MEMIT_CSK. GPT-2 Large and XL models edited using MEMIT_CSK outperform best-fine-tuned baselines by 10.97% and 10.73% F1 scores on PEP3k and 20Q datasets. In addition, we propose a novel evaluation dataset, PROBE\ SET, that contains unaffected and affected neighborhoods, affected paraphrases, and affected reasoning challenges. MEMIT_CSK performs well across the metrics while fine-tuning baselines show significant trade-offs between unaffected and affected metrics. These results suggest a compelling future direction for incorporating feedback about common sense into Transformers through direct model editing.

An important aspect of developing LLMs that interact with humans is to align models’ behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by PEW research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling relevant past user opinions in addition to user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. Our work opens up the research avenues to bring user opinions as an important ingredient in aligning language models.

Moral or ethical judgments rely heavily on the specific contexts in which they occur. Understanding varying shades of defeasible contextualizations (i.e., additional information that strengthens or attenuates the moral acceptability of an action) is critical to accurately represent the subtlety and intricacy of grounded human moral judgment in real-life scenarios. We introduce defeasible moral reasoning: a task to provide grounded contexts that make an action more or less morally acceptable, along with commonsense rationales that justify the reasoning. To elicit high-quality task data, we take an iterative self-distillation approach that starts from a small amount of unstructured seed knowledge from GPT-3 and then alternates between (1) self-distillation from student models; (2) targeted filtering with a critic model trained by human judgment (to boost validity) and NLI (to boost diversity); (3) self-imitation learning (to amplify the desired data quality). This process yields a student model that produces defeasible contexts with improved validity, diversity, and defeasibility. From this model we distill a high-quality dataset, 𝛿-Rules-of-Thumb, of 1.2M entries of contextualizations and rationales for 115K defeasible moral actions rated highly by human annotators 85.9% to 99.8% of the time. Using 𝛿-RoT we obtain a final student model that wins over all intermediate student models by a notable margin.

Despite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing language models with natural language feedback to guide them in repairing their outputs. Because human-generated critiques are expensive to obtain, researchers have devised learned critique generators in lieu of human critics while assuming one can train downstream models to utilize generated feedback. However, this approach does not apply to black-box or limited access models such as ChatGPT, as they cannot be fine-tuned. Moreover, in the era of large general-purpose language agents, fine-tuning is neither computationally nor spatially efficient as it results in multiple copies of the network. In this work, we introduce RL4F (Reinforcement Learning for Feedback), a multi-agent collaborative framework where the critique generator is trained to maximize end-task performance of GPT-3, a fixed model more than 200 times its size. RL4F produces critiques that help GPT-3 revise its outputs. We study three datasets for action planning, summarization and alphabetization and show relative improvements up to 10% in multiple text similarity metrics over other learned, retrieval-augmented or prompting-based critique generators.

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

Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TellMeWhy dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 and GPT3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models. Injecting external knowledge helps models of various sizes, but the amount of improvement decreases with larger model size. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.

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.

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.

Scripts – prototypical event sequences describing everyday activities – have been shown to help understand narratives by providing expectations, resolving ambiguity, and filling in unstated information. However, to date they have proved hard to author or extract from text. In this work, we demonstrate for the first time that pre-trained neural language models can be finetuned to generate high-quality scripts, at varying levels of granularity, for a wide range of everyday scenarios (e.g., bake a cake). To do this, we collect a large (6.4k) crowdsourced partially ordered scripts (named proScript), that is substantially larger than prior datasets, and develop models that generate scripts by combining language generation and graph structure prediction. We define two complementary tasks: (i) edge prediction: given a scenario and unordered events, organize the events into a valid (possibly partial-order) script, and (ii) script generation: given only a scenario, generate events and organize them into a (possibly partial-order) script. Our experiments show that our models perform well (e.g., F1=75.7 on task (i)), illustrating a new approach to overcoming previous barriers to script collection. We also show that there is still significant room for improvement toward human level performance. Together, our tasks, dataset, and models offer a new research direction for learning script knowledge.

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.

We present the first dataset for tracking state changes in procedural text from arbitrary domains by using an unrestricted (open) vocabulary. For example, in a text describing fog removal using potatoes, a car window may transition between being foggy, sticky, opaque, and clear. Previous formulations of this task provide the text and entities involved, and ask how those entities change for just a small, pre-defined set of attributes (e.g., location), limiting their fidelity. Our solution is a new task formulation where given just a procedural text as input, the task is to generate a set of state change tuples (entity, attribute, before-state, after-state) for each step, where the entity, attribute, and state values must be predicted from an open vocabulary. Using crowdsourcing, we create OPENPI, a high-quality (91.5% coverage as judged by humans and completely vetted), and large-scale dataset comprising 29,928 state changes over 4,050 sentences from 810 procedural real-world paragraphs from WikiHow.com. A current state-of-the-art generation model on this task achieves 16.1% F1 based on BLEU metric, leaving enough room for novel model architectures.

Our goal is to explain the effects of perturbations in procedural text, e.g., given a passage describing a rabbit’s life cycle, explain why illness (the perturbation) may reduce the rabbit population (the effect). Although modern systems are able to solve the original prediction task well (e.g., illness results in less rabbits), the explanation task - identifying the causal chain of events from perturbation to effect - remains largely unaddressed, and is the goal of this research. We present QUARTET, a system that constructs such explanations from paragraphs, by modeling the explanation task as a multitask learning problem. QUARTET constructs explanations from the sentences in the procedural text, achieving ~18 points better on explanation accuracy compared to several strong baselines on a recent process comprehension benchmark. On an end task on this benchmark, we show a surprising finding that good explanations do not have to come at the expense of end task performance, in fact leading to a 7% F1 improvement over SOTA.

Domain adaptation remains one of the most challenging aspects in the wide-spread use of Semantic Role Labeling (SRL) systems. Current state-of-the-art methods are typically trained on large-scale datasets, but their performances do not directly transfer to low-resource domain-specific settings. In this paper, we propose two approaches for domain adaptation in the biological domain that involves pre-training LSTM-CRF based on existing large-scale datasets and adapting it for a low-resource corpus of biological processes. Our first approach defines a mapping between the source labels and the target labels, and the other approach modifies the final CRF layer in sequence-labeling neural network architecture. We perform our experiments on ProcessBank dataset which contains less than 200 paragraphs on biological processes. We improve over the previous state-of-the-art system on this dataset by 21 F1 points. We also show that, by incorporating event-event relationship in ProcessBank, we are able to achieve an additional 2.6 F1 gain, giving us possible insights into how to improve SRL systems for biological process using richer annotations.

Our goal is to better comprehend procedural text, e.g., a paragraph about photosynthesis, by not only predicting what happens, but *why* some actions need to happen before others. Our approach builds on a prior process comprehension framework for predicting actions’ effects, to also identify subsequent steps that those effects enable. We present our new model (XPAD) that biases effect predictions towards those that (1) explain more of the actions in the paragraph and (2) are more plausible with respect to background knowledge. We also extend an existing benchmark dataset for procedural text comprehension, ProPara, by adding the new task of explaining actions by predicting their dependencies. We find that XPAD significantly outperforms prior systems on this task, while maintaining the performance on the original task in ProPara. The dataset is available at http://data.allenai.org/propara

We introduce WIQA, the first large-scale dataset of “What if...” questions over procedural text. WIQA contains a collection of paragraphs, each annotated with multiple influence graphs describing how one change affects another, and a large (40k) collection of “What if...?” multiple-choice questions derived from these. For example, given a paragraph about beach erosion, would stormy weather hasten or decelerate erosion? WIQA contains three kinds of questions: perturbations to steps mentioned in the paragraph; external (out-of-paragraph) perturbations requiring commonsense knowledge; and irrelevant (no effect) perturbations. We find that state-of-the-art models achieve 73.8% accuracy, well below the human performance of 96.3%. We analyze the challenges, in particular tracking chains of influences, and present the dataset as an open challenge to the community.

Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe). This task is challenging as the world is changing throughout the text, and despite recent advances, current systems still struggle with this task. Our approach is to leverage the fact that, for many procedural texts, multiple independent descriptions are readily available, and that predictions from them should be consistent (label consistency). We present a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model. Evaluation on a standard benchmark dataset for procedural text, ProPara (Dalvi et al., 2018), shows that our approach significantly improves prediction performance (F1) over prior state-of-the-art systems.

We present a new dataset and models for comprehending paragraphs about processes (e.g., photosynthesis), an important genre of text describing a dynamic world. The new dataset, ProPara, is the first to contain natural (rather than machine-generated) text about a changing world along with a full annotation of entity states (location and existence) during those changes (81k datapoints). The end-task, tracking the location and existence of entities through the text, is challenging because the causal effects of actions are often implicit and need to be inferred. We find that previous models that have worked well on synthetic data achieve only mediocre performance on ProPara, and introduce two new neural models that exploit alternative mechanisms for state prediction, in particular using LSTM input encoding and span prediction. The new models improve accuracy by up to 19%. We are releasing the ProPara dataset and our models to the community.

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent systems have shown impressive progress in this task, their predictions can be globally inconsistent or highly improbable. In this paper, we show how the predicted effects of actions in the context of a paragraph can be improved in two ways: (1) by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and (2) by biasing reading with preferences from large-scale corpora (e.g., trees rarely move). Unlike earlier methods, we treat the problem as a neural structured prediction task, allowing hard and soft constraints to steer the model away from unlikely predictions. We show that the new model significantly outperforms earlier systems on a benchmark dataset for procedural text comprehension (+8% relative gain), and that it also avoids some of the nonsensical predictions that earlier systems make.

Our goal is to construct a domain-targeted, high precision knowledge base (KB), containing general (subject,predicate,object) statements about the world, in support of a downstream question-answering (QA) application. Despite recent advances in information extraction (IE) techniques, no suitable resource for our task already exists; existing resources are either too noisy, too named-entity centric, or too incomplete, and typically have not been constructed with a clear scope or purpose. To address these, we have created a domain-targeted, high precision knowledge extraction pipeline, leveraging Open IE, crowdsourcing, and a novel canonical schema learning algorithm (called CASI), that produces high precision knowledge targeted to a particular domain - in our case, elementary science. To measure the KB’s coverage of the target domain’s knowledge (its “comprehensiveness” with respect to science) we measure recall with respect to an independent corpus of domain text, and show that our pipeline produces output with over 80% precision and 23% recall with respect to that target, a substantially higher coverage of tuple-expressible science knowledge than other comparable resources. We have made the KB publicly available.