We present a practical distillation approach to fine-tune LLMs for invoking tools in real-time applications. We focus on visual editing tasks; specifically, we modify images and videos by interpreting user stylistic requests, specified in natural language (“golden hour”), using an LLM to select the appropriate tools and their parameters to achieve the desired visual effect.We found that proprietary LLMs such as GPT-3.5-Turbo show potential in this task, but their high cost and latency make them unsuitable for real-time applications.In our approach, we fine-tune a (smaller) student LLM with guidance from a (larger) teacher LLM and behavioral signals.We introduce offline metrics to evaluate student LLMs. Both online and offline experiments show that our student models manage to match the performance of our teacher model (GPT-3.5-Turbo), significantly reducing costs and latency.Lastly, we show that fine-tuning was improved by 25% in low-data regimes using augmentation.

Recent advances in LLMs have led to an abundance of evaluation benchmarks, which typically rely on a single instruction template per task. We create a large-scale collection of instruction paraphrases and comprehensively analyze the brittleness introduced by single-prompt evaluations across 6.5M instances, involving 20 different LLMs and 39 tasks from 3 benchmarks. We find that different instruction templates lead to very different performance, both absolute and relative. Instead, we propose a set of diverse metrics on multiple instruction paraphrases, specifically tailored for different use cases (e.g., LLM vs. downstream development), ensuring a more reliable and meaningful assessment of LLM capabilities. We show that our metrics provide new insights into the strengths and limitations of current LLMs.

Analogy-making is central to human cognition, allowing us to adapt to novel situations – an ability that current AI systems still lack. Most analogy datasets today focus on simple analogies (e.g., word analogies); datasets including complex types of analogies are typically manually curated and very small. We believe that this holds back progress in computational analogy.In this work, we design a data generation pipeline, ParallelPARC (Parallel Paragraph Creator) leveraging state-of-the-art Large Language Models (LLMs) to create complex, paragraph-based analogies, as well as distractors, both simple and challenging. We demonstrate our pipeline and create ProPara-Logy, a dataset of analogies between scientific processes. We publish a gold-set, validated by humans, and a silver-set, generated automatically. We test LLMs’ and humans’ analogy recognition in binary and multiple-choice settings, and found that humans outperform the best models (∼13% gap) after a light supervision. We demonstrate that our silver-set is useful for training models. Lastly, we show challenging distractors confuse LLMs, but not humans. We hope our pipeline will encourage research in this emerging field.

When customers search online for a product they are not familiar with, their needs are often expressed through subjective product attributes, such as ”picture quality” for a TV or ”easy to clean” for a sofa. In contrast, the product catalog in online stores includes objective attributes such as ”screen resolution” or ”material”. In this work, we aim to find a link between the objective product catalog and the subjective needs of the customers, to help customers better understand the product space using their own words. We apply correlation-based methods to the store’s product catalog and product reviews in order to find the best potential links between objective and subjective attributes; next, Large Language Models (LLMs) reduce spurious correlations by incorporating common sense and world knowledge (e.g., picture quality is indeed affected by screen resolution, and 8k is the best one). We curate a dataset for this task and show that our combined approach outperforms correlation-only and causation-only approaches.

Figures of speech such as metaphors, similes, and idioms are integral parts of human communication. They are ubiquitous in many forms of discourse, allowing people to convey complex, abstract ideas and evoke emotion. As figurative forms are often conveyed through multiple modalities (e.g., both text and images), understanding multimodal figurative language is an important AI challenge, weaving together profound vision, language, commonsense and cultural knowledge. In this work, we develop the Image Recognition of Figurative Language (IRFL) dataset. We leverage human annotation and an automatic pipeline we created to generate a multimodal dataset, and introduce two novel tasks as a benchmark for multimodal figurative language understanding. We experimented with state-of-the-art vision and language models and found that the best (22%) performed substantially worse than humans (97%). We release our dataset, benchmark, and code in hopes of driving the development of models that can better understand figurative language.

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular, state-of-the-art large language models (LLMs) work at the level of tokens, not concepts. In this work, we analyze how well contemporary LLMs capture human concepts and their structure. We then discuss ways to develop concept-aware LLMs, taking place at different stages of the pipeline. We sketch a method for pretraining LLMs using concepts, and also explore the simpler approach that uses the output of existing LLMs. Despite its simplicity, our proof-of-concept is shown to better match human intuition, as well as improve the robustness of predictions. These preliminary results underscore the promise of concept-aware LLMs.

Analogy is one of the core capacities of human cognition; when faced with new situations, we often transfer prior experience from other domains. Most work on computational analogy relies heavily on complex, manually crafted input. In this work, we relax the input requirements, requiring only names of entities to be mapped. We automatically extract commonsense representations and use them to identify a mapping between the entities. Unlike previous works, our framework can handle partial analogies and suggest new entities to be added. Moreover, our method’s output is easily interpretable, allowing for users to understand why a specific mapping was chosen. Experiments show that our model correctly maps 81.2% of classical 2x2 analogy problems (guess level=50%). On larger problems, it achieves 77.8% accuracy (mean guess level=13.1%). In another experiment, we show our algorithm outperforms human performance, and the automatic suggestions of new entities resemble those suggested by humans. We hope this work will advance computational analogy by paving the way to more flexible, realistic input requirements, with broader applicability.

Analogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference – abilities lacking in even the best AI systems today. Much research has suggested that analogies are key to non-brittle systems that can adapt to new domains. Despite their importance, analogies received little attention in the NLP community, with most research focusing on simple word analogies. Work that tackled more complex analogies relied heavily on manually constructed, hard-to-scale input representations.In this work, we explore a more realistic, challenging setup: our input is a pair of natural language procedural texts, describing a situation or a process (e.g., how the heart works/how a pump works). Our goal is to automatically extract entities and their relations from the text and find a mapping between the different domains based on relational similarity (e.g., blood is mapped to water). We develop an interpretable, scalable algorithm and demonstrate that it identifies the correct mappings 87% of the time for procedural texts and 94% for stories from cognitive-psychology literature. We show it can extract analogies from a large dataset of procedural texts, achieving 79% precision (analogy prevalence in data: 3%). Lastly, we demonstrate that our algorithm is robust to paraphrasing the input texts

Can we teach models designed for language understanding tasks to track and improve their beliefs through intermediate points in text? Besides making their inner workings more transparent, this would also help make models more reliable and consistent. To this end, we propose a representation learning framework called breakpoint modeling that allows for efficient and robust learning of this type. Given any text encoder and data marked with intermediate states (breakpoints) along with corresponding textual queries viewed as true/false propositions (i.e., the candidate intermediate beliefs of a model), our approach trains models in an efficient and end-to-end fashion to build intermediate representations that facilitate direct querying and training of beliefs at arbitrary points in text, alongside solving other end-tasks. We evaluate breakpoint modeling on a diverse set of NLU tasks including relation reasoning on Cluttr and narrative understanding on bAbI. Using novel proposition prediction tasks alongside these end-tasks, we show the benefit of our T5-based breakpoint transformer over strong conventional representation learning approaches in terms of processing efficiency, belief accuracy, and belief consistency, all with minimal to no degradation on the end-task. To show the feasibility of incorporating our belief tracker into more complex reasoning pipelines, we also obtain state-of-the-art performance on the three-tiered reasoning challenge for the recent TRIP benchmark (23-32% absolute improvement on Tasks 2-3).

Humor is an inherently social phenomenon, with humorous utterances shaped by what is socially and culturally accepted. Understanding humor is an important NLP challenge, with many applications to human-computer interactions. In this work we explore humor in the context of Cards Against Humanity – a party game where players complete fill-in-the-blank statements using cards that can be offensive or politically incorrect.We introduce a novel dataset of 300,000 online games of Cards Against Humanity, including 785K unique jokes, analyze it and provide insights. We trained machine learning models to predict the winning joke per game, achieving performance twice as good (20%) as random, even without any user information.On the more difficult task of judging novel cards, we see the models’ ability to generalize is moderate. Interestingly, we find that our models are primarily focused on punchline card, with the context having little impact.Analyzing feature importance, we observe that short, crude, juvenile punchlines tend to win.

While neural language models often perform surprisingly well on natural language understanding (NLU) tasks, their strengths and limitations remain poorly understood. Controlled synthetic tasks are thus an increasingly important resource for diagnosing model behavior. In this work we focus on story understanding, a core competency for NLU systems. However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation. We develop Dyna-bAbI, a dynamic framework providing fine-grained control over task generation in bAbI. We demonstrate our ideas by constructing three new tasks requiring compositional generalization, an important evaluation setting absent from the original benchmark. We tested both special-purpose models developed for bAbI as well as state-of-the-art pre-trained methods, and found that while both approaches solve the original tasks (99% accuracy), neither approach succeeded in the compositional generalization setting, indicating the limitations of the original training data. We explored ways to augment the original data, and found that though diversifying training data was far more useful than simply increasing dataset size, it was still insufficient for driving robust compositional generalization (with 70% accuracy for complex compositions). Our results underscore the importance of highly controllable task generators for creating robust NLU systems through a virtuous cycle of model and data development.

Humor is an important social phenomenon, serving complex social and psychological functions. However, despite being studied for millennia humor is computationally not well understood, often considered an AI-complete problem. In this work, we introduce a novel setting in humor mining: automatically detecting funny and unusual scientific papers. We are inspired by the Ig Nobel prize, a satirical prize awarded annually to celebrate funny scientific achievements (example past winner: “Are cows more likely to lie down the longer they stand?”). This challenging task has unique characteristics that make it particularly suitable for automatic learning. We construct a dataset containing thousands of funny papers and use it to learn classifiers, combining findings from psychology and linguistics with recent advances in NLP. We use our models to identify potentially funny papers in a large dataset of over 630,000 articles. The results demonstrate the potential of our methods, and more broadly the utility of integrating state-of-the-art NLP methods with insights from more traditional disciplines

A snowclone is a customizable phrasal template that can be realized in multiple, instantly recognized variants. For example, “* is the new *" (Orange is the new black, 40 is the new 30). Snowclones are extensively used in social media. In this paper, we study snowclones originating from pop-culture quotes; our goal is to automatically detect cultural references in text. We introduce a new, publicly available data set of pop-culture quotes and their corresponding snowclone usages and train models on them. We publish code for Catchphrase, an internet browser plugin to automatically detect and mark references in real-time, and examine its performance via a user study. Aside from assisting people to better comprehend cultural references, we hope that detecting snowclones can complement work on paraphrasing and help tackling long-standing questions in social science about the dynamics of information propagation.

While natural language understanding (NLU) is advancing rapidly, today’s technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability, and generalization. This work proposes an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL). According to ECL, natural language is inherently executable (like programming languages), driven by mental simulation and metaphoric mappings over hierarchical compositions of structures and schemata learned through embodied interaction. This position paper argues that the use of grounding by metaphoric reasoning and simulation will greatly benefit NLU systems, and proposes a system architecture along with a roadmap towards realizing this vision.

Spoken languages are ever-changing, with new words entering them all the time. However, coming up with new words (neologisms) today relies exclusively on human creativity. In this paper we propose a system to automatically suggest neologisms. We focus on the Hebrew language as a test case due to the unusual regularity of its noun formation. User studies comparing our algorithm to experts and non-experts demonstrate that our algorithm is capable of generating high-quality outputs, as well as enhance human creativity. More broadly, we seek to inspire more computational work around the topic of linguistic creativity, which we believe offers numerous unexplored opportunities.

Understanding procedural text requires tracking entities, actions and effects as the narrative unfolds. We focus on the challenging real-world problem of action-graph extraction from materials science papers, where language is highly specialized and data annotation is expensive and scarce. We propose a novel approach, Text2Quest, where procedural text is interpreted as instructions for an interactive game. A learning agent completes the game by executing the procedure correctly in a text-based simulated lab environment. The framework can complement existing approaches and enables richer forms of learning compared to static texts. We discuss potential limitations and advantages of the approach, and release a prototype proof-of-concept, hoping to encourage research in this direction.