Abstract The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior stems from a reporting bias in their training data. That is, how people communicate about visual content by default omits tacit information needed to supervise some types of reasoning; e.g., “at the game today!” is a more likely caption than “a photo of 37 people standing behind a field”. We investigate the data underlying the popular VLMs OpenCLIP, LLaVA-1.5 and Molmo through the lens of theories from pragmatics, and find that reporting bias results in insufficient representation of four reasoning skills (spatial, temporal, negation, and counting), despite the corpora being of web-scale, and/or synthetically generated. With a set of curated benchmarks, we demonstrate that: (i) VLMs perform poorly on the aforementioned types of reasoning suppressed in the training data by reporting bias; (ii) contrary to popular belief, scaling data size, model size, and to multiple languages does not result in emergence of these skills by default; but, promisingly, (iii) incorporating annotations specifically collected to obtain tacit information is effective. Our findings highlight the need for more intentional training data curation methods, rather than counting on scale for emergence of reasoning capabilities.

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI systems, distinguishing between epistemic uncertainty (arising from a lack of information) and aleatoric uncertainty (due to inherent unpredictability), and further explore finer categories within. Based on this taxonomy, we synthesize a benchmark dataset, CertainlyUncertain, featuring 178K visual question answering (VQA) samples as contrastive pairs. This is achieved by 1) inpainting images to make previously answerable questions into unanswerable ones; and 2) using image captions to prompt large language models for both answerable and unanswerable questions. Additionally, we introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error, to address the shortcomings of existing metrics. Despite the recent rapid progress in vision-language models (VLMs), evaluations on our benchmark show that they perform poorly in uncertain scenarios. Further experiments demonstrate that supervised fine-tuning with CertainlyUncertain enhances the performance of VLMs, and reduces the calibration error. These improvements extend beyond our benchmark to existing refusal-oriented datasets and show positive results on reducing hallucinations, while maintaining performance on standard VQA benchmarks. Our work underscores the importance of addressing uncertainty in vision-language AI systems to improve their reliability and trustworthiness in real-world applications.

Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be prompted like an LM. To train Promptriever, we curate and release a new instance-level instruction training set from MS MARCO, spanning nearly 500k instances. Promptriever not only achieves strong performance on standard retrieval tasks, but also follows instructions. We observe: (1) large gains (reaching SoTA) on following detailed relevance instructions (+14.3 p-MRR / +3.1 nDCG on FollowIR), (2) significantly increased robustness to lexical choices/phrasing in the query+instruction (+12.9 Robustness@10 on InstructIR), and (3) the ability to perform hyper-parameter search via prompting to reliably improve retrieval performance (+1.4 average increase on BEIR). Promptriever demonstrates that retrieval models can be controlled with prompts on a per-query basis, setting the stage for future work aligning LM prompting techniques with information retrieval.

Dirk Groeneveld, Iz Beltagy, Evan Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, William Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah Smith, Hannaneh Hajishirzi. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant to the argument, and relevance can only be understood within the context of a broader argumentative structure. While visual arguments are readily appreciated by human audiences, we ask: are today’s AI capable of similar understanding?We present VisArgs, a dataset of 1,611 images annotated with 5,112 visual premises (with regions), 5,574 commonsense premises, and reasoning trees connecting them into structured arguments. We propose three tasks for evaluating visual argument understanding: premise localization, premise identification, and conclusion deduction.Experiments show that 1) machines struggle to capture visual cues: GPT-4-O achieved 78.5% accuracy, while humans reached 98.0%. Models also performed 19.5% worse when distinguishing between irrelevant objects within the image compared to external objects. 2) Providing relevant visual premises improved model performance significantly.

Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant scales (e.g., 175B parameter GPT-3); and 2) focuses largely on downstream performance, ignoring the semantics of the rationales themselves, e.g., are they faithful, true, and helpful for humans? In this work, we enable small-scale LMs (∼200x smaller than GPT-3) to generate rationales that not only improve downstream task performance, but are also more plausible, consistent, and diverse, assessed both by automatic and human evaluation. Our method, MaRio (Multi-rewArd RatIOnalization), is a multi-reward conditioned self-rationalization algorithm that optimizes multiple distinct properties like plausibility, diversity and consistency. Results on three difficult question-answering datasets StrategyQA, QuaRel and OpenBookQA show that not only does MaRio improve task accuracy, but it also improves the self-rationalization quality of small LMs across the aforementioned axes better than a supervised fine-tuning (SFT) baseline. Extensive human evaluations confirm that MaRio rationales are preferred vs. SFT rationales, as well as qualitative improvements in plausibility and consistency.

Chatbots such as GPT-4 and ChatGPT are now serving millions of users. Despite their widespread use, there remains a lack of public datasets showcasing how these tools are used by a population of users in practice. To bridge this gap, we offered free access to ChatGPT for online users in exchange for their affirmative, consensual opt-in to anonymously collect their chat transcripts and request headers. From this, we compiled WildChat, a corpus of 1 million user-ChatGPT conversations, which consists of over 2.5 million interaction turns. We compare WildChat with other popular user-chatbot interaction datasets, and find that our dataset offers the most diverse user prompts, contains the largest number of languages, and presents the richest variety of potentially toxic use-cases for researchers to study. In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses, alongside request headers. This augmentation allows for more detailed analysis of user behaviors across different geographical regions and temporal dimensions. Finally, because it captures a broad range of use cases, we demonstrate the dataset’s potential utility in fine-tuning instruction-following models. WildChat is released at https://wildchat.allen.ai under AI2 ImpACT Licenses.

Wenting Zhao, Justin T. Chiu, Jena Hwang, Faeze Brahman, Jack Hessel, Sanjiban Choudhury, Yejin Choi, Xiang Lorraine Li, Alane Suhr. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of ``unsafe'' queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this taxonomy to develop a new evaluation suite of 1000 noncompliance prompts. We find that most existing models show significantly high compliance rates in certain previously understudied categories with models like GPT-4 incorrectly complying with as many as 30\% of requests.To address these gaps, we explore different training strategies using a synthetically-generated training set of requests and expected noncompliant responses. Our experiments demonstrate that while direct finetuning of instruction-tuned models can lead to both over-refusal and a decline in general capabilities, using parameter efficient methods like low rank adapters helps to strike a good balance between appropriate noncompliance and other capabilities.

Jack Hessel, Ana Marasovic, Jena D. Hwang, Lillian Lee, Jeff Da, Rowan Zellers, Robert Mankoff, Yejin Choi. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Liunian Harold Li, Jack Hessel, Youngjae Yu, Xiang Ren, Kai-Wei Chang, Yejin Choi. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Language models are capable of commonsense reasoning: while domain-specific models can learn from explicit knowledge (e.g. commonsense graphs [6] ethical norms [25]), and larger models like GPT-3 [7] mani-fest broad commonsense reasoning capacity. Can their knowledge be extended to multimodal inputs such as images and audio without paired domain data? In this work, we propose‡ESPER (Extending Sensory PErception with Reinforcement learning) which enables text-only pretrained models to address multimodal tasks such as visual commonsense reasoning. Our key novelty is to use rein-forcement learning to align multimodal inputs to language model generations without direct supervision: for example, our reward optimization relies only on cosine similarity derived from CLIP [52] and requires no additional paired (image, text) data. Experiments demonstrate that ESPER outperforms baselines and prior work on a variety of multimodal text generation tasks ranging from captioning to commonsense reasoning; these include a new benchmark we collect and release, the ESP dataset, which tasks models with generating the text of several different domains for each image. Our code and data are publicly released at https://github.com/JiwanChung/esper.

Hyunwoo Kim, Jack Hessel, Liwei Jiang, Peter West, Ximing Lu, Youngjae Yu, Pei Zhou, Ronan Bras, Malihe Alikhani, Gunhee Kim, Maarten Sap, Yejin Choi. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Commonsense norms are defeasible by context: reading books is usually great, but not when driving a car.While contexts can be explicitly described in language, in embodied scenarios, contexts are often provided visually.This type of visually grounded reasoning about defeasible commonsense norms is generally easy for humans, but (as we show) poses a challenge for machines, as it necessitates both visual understanding and reasoning about commonsense norms.We construct a new multimodal benchmark for studying visual-grounded commonsense norms: NORMLENS.NORMLENS consists of 10K human judgments accompanied by freeform explanations covering 2K multimodal situations, and serves as a probe to address two questions: (1) to what extent can models align with average human judgment?and (2) how well can models explain their predicted judgments?We find that state-of-theart model judgments and explanations are not well-aligned with human annotation.Additionally, we present a new approach to better align models with humans by distilling social commonsense knowledge from large language models.The data and code are released at https://seungjuhan.me/normlens.

Performant vision-language (VL) models like CLIP represent captions using a single vector.How much information about language is lost in this bottleneck?We first curate CompPrompts, a set of increasingly compositional image captions that VL models should be able to capture (e.g., single object, to ob-ject+property, to multiple interacting objects).Then, we train text-only recovery probes that aim to reconstruct captions from single-vector text representations produced by several VL models.This approach does not require images, allowing us to test on a broader range of scenes compared to prior work.We find that: 1) CLIP's text encoder falls short on more compositional inputs, including object relationships, attribute-object association, counting, and negations; 2) some text encoders work significantly better than others; and 3) text-only recovery performance predicts multimodal matching performance on ControlledImCaps: a new evaluation benchmark we collect and release consisting of fine-grained compositional images and captions.Specifically, our results suggest textonly recoverability is a necessary (but not sufficient) condition for modeling compositional factors in contrastive VL models.We release our datasets and code.

Recent vision-language (VL) models are powerful, but can they reliably distinguish "right" from "left"?We curate three new corpora to quantify model comprehension of such basic spatial relations.These tests isolate spatial reasoning more precisely than existing datasets like VQAv2, e.g., our What'sUp benchmark contains sets of photographs varying only the spatial relations of objects, keeping their identity fixed (see Figure 1: models must comprehend not only the usual case of a dog under a table, but also, the same dog on top of the same table).We evaluate 18 VL models, finding that all perform poorly, e.g., BLIP finetuned on VQAv2, which nears human parity on VQAv2, achieves 56% accuracy on our benchmarks vs. humans at 99%.We conclude by studying causes of this surprising behavior, finding: 1) that popular vision-language pretraining corpora like LAION-2B contain little reliable data for learning spatial relationships; and 2) that basic modeling interventions like up-weighting preposition-containing instances or fine-tuning on our corpora are not sufficient to address the challenges our benchmarks pose.We are hopeful that these corpora will facilitate further research, and we release our data and code at https://github.com/amitakamath/ whatsup_vlms.

Weird, unusual, and uncanny images pique the curiosity of observers because they challenge commonsense. For example, an image released during the 2022 world cup depicts the famous soccer stars Lionel Messi and Cristiano Ronaldo playing chess, which playfully violates our expectation that their competition should occur on the football field.1Humans can easily recognize and interpret these unconventional images, but can AI models do the same? We introduce WHOOPS!, a new dataset and benchmark for visual commonsense. The dataset is comprised of purposefully commonsense-defying images created by designers using publicly-available image generation tools like Midjourney. We consider several tasks posed over the dataset. In addition to image captioning, cross-modal matching, and visual question answering, we introduce a difficult explanation generation task, where models must identify and explain why a given image is unusual. Our results show that state-of-the-art models such as GPT3 and BLIP2 still lag behind human performance on WHOOPS!. We hope our dataset will inspire the development of AI models with stronger visual commonsense reasoning abilities.2

Visual information is central to conversation: body gestures and physical behaviour, for example, contribute to meaning that transcends words alone. To date, however, most neural conversational models are limited to just text. We introduce Champagne, a generative model of conversations that can account for visual contexts. To train Champagne, we collect and release YTD-18M, a large-scale corpus of 18M video-based dialogues. YTD-18M is constructed from web videos: crucial to our data collection pipeline is a pretrained language model that converts error-prone automatic transcripts to a cleaner dialogue format while maintaining meaning.Human evaluation reveals that YTD-18M is more sensible and specific than prior resources (MMDialog [17], 1M dialogues), while maintaining visual-groundedness. Experiments demonstrate that 1) Champagne learns to conduct conversation from YTD-18M; and 2) when fine-tuned, it achieves state-of-the-art results on four vision-language tasks focused on real-world conversations. We release data, models, and code at https://seungjuhan.me/champagne.

We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluating instruction-following vision-language models for real-world use. Our starting point is curating 70 "instruction families" that we envision instruction tuned vision-language models should be able to address. Extending beyond evaluations like VQAv2 and COCO, tasks range from basic recognition to game playing and creative generation. Following curation, our dataset comprises 592 test queries, each with a human-authored instruction-conditioned caption. These descriptions surface instruction-specific factors, e.g., for an instruction asking about the accessibility of a storefront for wheelchair users, the instruction-conditioned caption describes ramps/potential obstacles. These descriptions enable 1) collecting human-verified reference outputs for each instance; and 2) automatic evaluation of candidate multimodal generations using a text-only LLM, aligning with human judgment. We quantify quality gaps between models and references using both human and automatic evaluations; e.g., the top-performing instruction-following model wins against the GPT-4 reference in just 27% of the comparison. VisIT-Bench is dynamic to participate, practitioners simply submit their model's response on the project website; Data, code and leaderboard is available at https://visit-bench.github.io/.

Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to “point to" and access specific regions within images. This capability is important not only to support reference-grounded VL benchmarks, but also, for practical applications that require precise within-image reasoning. We build Localized Visual Commonsense model which allows users to specify (multiple) regions- as-input. We train our model by sampling localized commonsense knowledge from a large language model (LLM): specifically, we prompt a LLM to collect commonsense knowledge given a global literal image description and a local literal region description automatically generated by a set of VL models. This pipeline is scalable and fully automatic, as no aligned or human-authored image and text pairs are required. With a separately trained critic model that selects high quality examples, we find that training on the localized commonsense corpus expanded solely from images can successfully distill existing VL models to support a reference-as-input interface. Empirical results and human evaluations in zero-shot settings demonstrate that our distillation method results in more precise VL models of reasoning compared to a baseline of passing a generated referring expression.

In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on par with state-of-the-art proprietary models, these claims are often accompanied by limited evaluation, making it difficult to compare models across the board and determine the utility of various resources. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets ranging from manually curated (e.g., OpenAssistant) to synthetic and distilled (e.g., Alpaca) and systematically evaluate them on their factual knowledge, reasoning, multilinguality, coding, safety, and open-ended instruction following abilities through a collection of automatic, model-based, and human-based metrics. We further introduce Tülu, our best performing instruction-tuned model suite finetuned on a combination of high-quality open resources.Our experiments show that different instruction-tuning datasets can uncover or enhance specific skills, while no single dataset (or combination) provides the best performance across all evaluations. Interestingly, we find that model and human preference-based evaluations fail to reflect differences in model capabilities exposed by benchmark-based evaluations, suggesting the need for the type of systemic evaluation performed in this work. Our evaluations show that the best model in any given evaluation reaches on average 87% of ChatGPT performance, and 73% of GPT-4 performance, suggesting that further investment in building better base models and instruction-tuning data is required to close the gap. We release our instruction-tuned models, including a fully finetuned 65B Tülu, along with our code, data, and evaluation framework to facilitate future research.

In-context vision and language models like Flamingo support arbitrarily interleaved sequences of images and text as input.This format not only enables few-shot learning via interleaving independent supervised (image, text) examples, but also, more complex prompts involving interaction between images, e.g., ``What do image A and image B have in common?''To support this interface, pretraining occurs over web corpora that similarly contain interleaved images+text.To date, however, large-scale data of this form have not been publicly available.We release Multimodal C4, an augmentation of the popular text-only C4 corpus with images interleaved.We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives.Multimodal C4 spans everyday topics like cooking, travel, technology, etc. A manual inspection of a random sample of documents shows that a vast majority (88\%) of images are topically relevant, and that linear assignment frequently selects individual sentences specifically well-aligned with each image (80\%). After filtering NSFW images, ads, etc., the resulting corpus consists of 101.2M documents with 571M images interleaved in 43B English tokens.

As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce @MERLOT RESERVE, a model that represents videos jointly over time - through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos. Empirical results show that @MERLOT RESERVE learns strong multimodal representations. When finetuned, it sets state-of-the-art on Visual Commonsense Reasoning (VCR), TVQA, and Kinetics-600; outperforming prior work by 5%, 7%, and 1.5% respectively. Ablations show that these tasks benefit from audio pretraining - even VCR, a QA task centered around images (without sound). Moreover, our objective enables out-of-the-box prediction, revealing strong multimodal commonsense understanding. In a fully zero-shot setting, our model obtains competitive results on four video tasks, even outperforming supervised approaches on the recently proposed Situated Reasoning (STAR) benchmark. We analyze why audio enables better vision-language representations, suggesting significant opportunities for future research. We conclude by discussing ethical and societal implications of multimodal pretraining.

Peter West, Chandra Bhagavatula, Jack Hessel, Jena Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, Yejin Choi. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark Riedl, Yejin Choi. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Yanpeng Zhao, Jack Hessel, Youngjae Yu, Ximing Lu, Rowan Zellers, Yejin Choi. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a different sentiment than desired by the user. We consider the task of unlearning these misalignments by fine-tuning the language model on signals of what not to do. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property, while not straying too far from the original model. Quark alternates between (i) collecting samples with the current language model, (ii) sorting them into quantiles based on reward, with each quantile identified by a reward token prepended to the language model’s input, and (iii) using a standard language modeling loss on samples from each quantile conditioned on its reward token, while remaining nearby the original language model via a KL-divergence penalty. By conditioning on a high-reward token at generation time, the model generates text that exhibits less of the unwanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods like PPO, while relying only on standard language modeling primitives.

Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans.This is in contrast to the reference-free manner in which humans assess caption quality.In this paper, we report the surprising empirical finding that CLIP (Radford et al., 2021), a cross-modal model pretrained on 400M im-age+caption pairs from the web, can be used for robust automatic evaluation of image captioning without the need for references.Experiments spanning several corpora demonstrate that our new reference-free metric, CLIPScore, achieves the highest correlation with human judgements, outperforming existing reference-based metrics like CIDEr and SPICE.Information gain experiments demonstrate that CLIPScore, with its tight focus on image-text compatibility, is complementary to existing reference-based metrics that emphasize text-text similarities.Thus, we also present a reference-augmented version, RefCLIPScore, which achieves even higher correlation.Beyond literal description tasks, several case studies reveal domains where CLIPScore performs well (clip-art images, alt-text rating), but also where it is relatively weaker in comparison to reference-based metrics, e.g., news captions that require richer contextual knowledge.

As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner. By pretraining with a mix of both frame-level (spatial) and video-level (temporal) objectives, our model not only learns to match images to temporally corresponding words, but also to contextualize what is happening globally over time. As a result, MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets when finetuned. It also transfers well to the world of static images, allowing models to reason about the dynamic context behind visual scenes. On Visual Commonsense Reasoning, MERLOT~answers questions correctly with 80.6\% accuracy, outperforming state-of-the-art models of similar size by over 3\%, even those that make heavy use of auxiliary supervised data (like object bounding boxes).Ablation analyses demonstrate the complementary importance of: 1) training on videos versus static images; 2) scaling the magnitude and diversity of the pretraining video corpus; and 3) using diverse objectives that encourage full-stack multimodal reasoning, from the recognition to cognition level.

Modeling expressive cross-modal interactions seems crucial in multimodal tasks, such as visual question answering.However, sometimes high-performing black-box algorithms turn out to be mostly exploiting unimodal signals in the data.We propose a new diagnostic tool, empirical multimodally-additive function projection (EMAP), for isolating whether or not cross-modal interactions improve performance for a given model on a given task.This function projection modifies model predictions so that cross-modal interactions are eliminated, isolating the additive, unimodal structure.For seven image+text classification tasks (on each of which we set new state-ofthe-art benchmarks), we find that, in many cases, removing cross-modal interactions results in little to no performance degradation.Surprisingly, this holds even when expressive models, with capacity to consider interactions, otherwise outperform less expressive models; thus, performance improvements, even when present, often cannot be attributed to consideration of cross-modal feature interactions.We hence recommend that researchers in multimodal machine learning report the performance not only of unimodal baselines, but also the EMAP of their best-performing model.

Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks.Features are learned via prediction of grounded relationships between visual content and automatic speech recognition (ASR) tokens.However, prior pretraining work has been limited to only instructional videos; a priori, we expect this domain to be relatively "easy:" speakers in instructional videos will often reference the literal objects/actions being depicted.We ask: can similar models be trained on more diverse video corpora?And, if so, what types of videos are "grounded" and what types are not?We fit a representative pretraining model to the diverse YouTube8M dataset, and study its success and failure cases.We find that visualtextual grounding is indeed possible across previously unexplored video categories, and that pretraining on a more diverse set results in representations that generalize to both noninstructional and instructional domains.

Images can give us insights into the contextual meanings of words, but current imagetext grounding approaches require detailed annotations.Such granular annotation is rare, expensive, and unavailable in most domainspecific contexts.In contrast, unlabeled multiimage, multi-sentence documents are abundant.Can lexical grounding be learned from such documents, even though they have significant lexical and visual overlap?Working with a case study dataset of real estate listings, we demonstrate the challenge of distinguishing highly correlated grounded terms, such as "kitchen" and "bedroom", and introduce metrics to assess this document similarity.We present a simple unsupervised clusteringbased method that increases precision and recall beyond object detection and image tagging baselines when evaluated on labeled subsets of the dataset.The proposed method is particularly effective for local contextual meanings of a word, for example associating "granite" with countertops in the real estate dataset and with rocky landscapes in a Wikipedia dataset."kitchen" (18.4% labeled true) E: 72.9 AUC W: 52.7 AUC R: 21.1 AUC "outdoor" (16.9% labeled true) E: 68.5 AUC W: 20.0 AUC R: 13.2 AUC "washer" (1.6% labeled true)

Instructional videos get high-traffic on video sharing platforms, and prior work suggests that providing time-stamped, subtask annotations (e.g., "heat the oil in the pan") improves user experiences.However, current automatic annotation methods based on visual features alone perform only slightly better than constant prediction.Taking cues from prior work, we show that we can improve performance significantly by considering automatic speech recognition (ASR) tokens as input.Furthermore, jointly modeling ASR tokens and visual features results in higher performance compared to training individually on either modality.We find that unstated background information is better explained by visual features, whereas fine-grained distinctions (e.g., "add oil" vs. "add olive oil") are disambiguated more easily via ASR tokens.

Jack Hessel, Lillian Lee, David Mimno. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Jack Hessel, David Mimno, Lillian Lee. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

The content of today's social media is becoming more and more rich, increasingly mixing text, images, videos, and audio. It is an intriguing research question to model the interplay between these different modes in attracting user attention and engagement. But in order to pursue this study of multimodal content, we must also account for context: timing effects, community preferences, and social factors (e.g., which authors are already popular) also affect the amount of feedback and reaction that social-media posts receive. In this work, we separate out the influence of these non-content factors in several ways. First, we focus on ranking pairs of submissions posted to the same community in quick succession, e.g., within 30 seconds; this framing encourages models to focus on time-agnostic and community-specific content features. Within that setting, we determine the relative performance of author vs. content features. We find that victory usually belongs to "cats and captions," as visual and textual features together tend to outperform identity-based features. Moreover, our experiments show that when considered in isolation, simple unigram text features and deep neural network visual features yield the highest accuracy individually, and that the combination of the two modalities generally leads to the best accuracies overall.