We present the outcomes of the Multimodal Figurative Language Shared Task held at the 4th Workshop on Figurative Language Processing (FigLang 2024) co-located at NAACL 2024. The task utilized the V-FLUTE dataset which is comprised of <image, text> pairs that use figurative language and includes detailed textual explanations for the entailment or contradiction relationship of each pair. The challenge for participants was to develop models capable of accurately identifying the visual entailment relationship in these multimodal instances and generating persuasive free-text explanations. The results showed that the participants’ models significantly outperformed the initial baselines in both automated and human evaluations. We also provide an overview of the systems submitted and analyze the results of the evaluations. All participating systems outperformed the LLaVA-ZS baseline, provided by us in F1-score.

While state-of-the-art large language models (LLMs) can excel at adapting text from one style to another, current work does not address the explainability of style transfer models. Recent work has explored generating textual explanations from larger teacher models and distilling them into smaller student models. One challenge with such approach is that LLM outputs may contain errors that require expertise to correct, but gathering and incorporating expert feedback is difficult due to cost and availability. To address this challenge, we propose ICLEF, a novel human-AI collaboration approach to model distillation that incorporates scarce expert human feedback by combining in-context learning and model self-critique. We show that our method leads to generation of high-quality synthetic explainable style transfer datasets for formality (E-GYAFC) and subjective bias (E-WNC). Via automatic and human evaluation, we show that specialized student models fine-tuned on our datasets outperform generalist teacher models on the explainable style transfer task in one-shot settings, and perform competitively compared to few-shot teacher models, highlighting the quality of the data and the role of expert feedback. In an extrinsic task of authorship attribution, we show that explanations generated by smaller models fine-tuned on E-GYAFC are more predictive of authorship than explanations generated by few-shot teacher models.

Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the symbols. We propose a new task of generating visual metaphors from linguistic metaphors. This is a challenging task for diffusion-based text-to-image models, such as DALL⋅E 2, since it requires the ability to model implicit meaning and compositionality. We propose to solve the task through the collaboration between Large Language Models (LLMs) and Diffusion Models: Instruct GPT-3 (davinci-002) with Chain-of-Thought prompting generates text that represents a visual elaboration of the linguistic metaphor containing the implicit meaning and relevant objects, which is then used as input to the diffusion-based text-to-image models. Using a human-AI collaboration framework, where humans interact both with the LLM and the top-performing diffusion model, we create a high-quality dataset containing 6,476 visual metaphors for 1,540 linguistic metaphors and their associated visual elaborations. Evaluation by professional illustrators shows the promise of LLM-Diffusion Model collaboration for this task.To evaluate the utility of our Human-AI collaboration framework and the quality of our dataset, we perform both an intrinsic human-based evaluation and an extrinsic evaluation using visual entailment as a downstream task.

Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of instructions) 2) grounding (the need to localize where the edit has to be performed), 3) faithfulness (the need to preserve the elements of the image not affected by the edit instruction). Current approaches focusing on image editing with natural language instructions rely on automatically generated paired data, which, as shown in our investigation, is noisy and sometimes nonsensical, exacerbating the above issues. Building on recent advances in segmentation, Chain-of-Thought prompting, and visual question answering, we significantly improve the quality of the paired data. In addition, we enhance the supervision signal by highlighting parts of the image that need to be changed by the instruction. The model fine-tuned on the improved data is capable of performing fine-grained object-centric edits better than state-of-the-art baselines, mitigating the problems outlined above, as shown by automatic and human evaluations. Moreover, our model is capable of generalizing to domains unseen during training, such as visual metaphors.

Designing systems that can reason across cultures requires that they are grounded in the norms of the contexts in which they operate. However, current research on developing computational models of social norms has primarily focused on American society. Here, we propose a novel approach to discover and compare descriptive social norms across Chinese and American cultures. We demonstrate our approach by leveraging discussions on a Chinese Q&A platform—Zhihu—and the existing SocialChemistry dataset as proxies for contrasting cultural axes, align social situations cross-culturally, and extract social norms from texts using in-context learning. Embedding Chain-of-Thought prompting in a human-AI collaborative framework, we build a high-quality dataset of 3,069 social norms aligned with social situations across Chinese and American cultures alongside corresponding free-text explanations. To test the ability of models to reason about social norms across cultures, we introduce the task of explainable social norm entailment, showing that existing models under 3B parameters have significant room for improvement in both automatic and human evaluation. Further analysis of cross-cultural norm differences based on our dataset shows empirical alignment with the social orientations framework, revealing several situational and descriptive nuances in norms across these cultures.

Social norms fundamentally shape interpersonal communication. We present NormDial, a high-quality dyadic dialogue dataset with turn-by-turn annotations of social norm adherences and violations for Chinese and American cultures. Introducing the task of social norm observance detection, our dataset is synthetically generated in both Chinese and English using a human-in-the-loop pipeline by prompting large language models with a small collection of expert-annotated social norms. We show that our generated dialogues are of high quality through human evaluation and further evaluate the performance of existing large language models on this task. Our findings point towards new directions for understanding the nuances of social norms as they manifest in conversational contexts that span across languages and cultures.

Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a.k.a. natural language inference (NLI)). However, similar to classical RTE/NLI datasets they suffer from spurious correlations and annotation artifacts. To tackle this problem, work on NLI has built explanation-based datasets such as eSNLI, allowing us to probe whether language models are right for the right reasons. Yet no such data exists for figurative language, making it harder to assess genuine understanding of such expressions. To address this issue, we release FLUTE, a dataset of 9,000 figurative NLI instances with explanations, spanning four categories: Sarcasm, Simile, Metaphor, and Idioms. We collect the data through a Human-AI collaboration framework based on GPT-3, crowd workers, and expert annotators. We show how utilizing GPT-3 in conjunction with human annotators (novices and experts) can aid in scaling up the creation of datasets even for such complex linguistic phenomena as figurative language. The baseline performance of the T5 model fine-tuned on FLUTE shows that our dataset can bring us a step closer to developing models that understand figurative language through textual explanations.

We present the results of the Shared Task on Understanding Figurative Language that we conducted as a part of the 3rd Workshop on Figurative Language Processing (FigLang 2022) at EMNLP 2022. The shared task is based on the FLUTE dataset (Chakrabarty et al., 2022), which consists of NLI pairs containing figurative language along with free text explanations for each NLI instance. The task challenged participants to build models that are able to not only predict the right label for a figurative NLI instance, but also generate a convincing free-text explanation. The participants were able to significantly improve upon provided baselines in both automatic and human evaluation settings. We further summarize the submitted systems and discuss the evaluation results.

We introduce a FEVER-like dataset COVID-Fact of 4,086 claims concerning the COVID-19 pandemic. The dataset contains claims, evidence for the claims, and contradictory claims refuted by the evidence. Unlike previous approaches, we automatically detect true claims and their source articles and then generate counter-claims using automatic methods rather than employing human annotators. Along with our constructed resource, we formally present the task of identifying relevant evidence for the claims and verifying whether the evidence refutes or supports a given claim. In addition to scientific claims, our data contains simplified general claims from media sources, making it better suited for detecting general misinformation regarding COVID-19. Our experiments indicate that COVID-Fact will provide a challenging testbed for the development of new systems and our approach will reduce the costs of building domain-specific datasets for detecting misinformation.

Despite constant improvements in machine translation quality, automatic poetry translation remains a challenging problem due to the lack of open-sourced parallel poetic corpora, and to the intrinsic complexities involved in preserving the semantics, style and figurative nature of poetry. We present an empirical investigation for poetry translation along several dimensions: 1) size and style of training data (poetic vs. non-poetic), including a zero-shot setup; 2) bilingual vs. multilingual learning; and 3) language-family-specific models vs. mixed-language-family models. To accomplish this, we contribute a parallel dataset of poetry translations for several language pairs. Our results show that multilingual fine-tuning on poetic text significantly outperforms multilingual fine-tuning on non-poetic text that is 35X larger in size, both in terms of automatic metrics (BLEU, BERTScore, COMET) and human evaluation metrics such as faithfulness (meaning and poetic style). Moreover, multilingual fine-tuning on poetic data outperforms bilingual fine-tuning on poetic data.