Search

Modern language models (LMs) pose a new challenge in capability assessment. Static benchmarks inevitably saturate without providing confidence in the deployment tolerances of LM-based systems, but developers nonetheless claim that their models have generalized traits such as reasoning or open-domain language understanding based on these flawed metrics. The science and practice of LMs requires a new approach to benchmarking which measures specific capabilities with dynamic assessments. To be confident in our metrics, we need a new discipline of model metrology -- one which focuses on how to generate benchmarks that predict performance under deployment. Motivated by our evaluation criteria, we outline how building a community of model metrology practitioners -- one focused on building tools and studying how to measure system capabilities -- is the best way to meet these needs to and add clarity to the AI discussion., Comment: Conference paper at COLM 2024

Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the ways that these capabilities combine are not always intuitive and warrant direct investigation. One understudied capability in VLMs is visual spatial planning -- the ability to comprehend the spatial arrangements of objects and devise action plans to achieve desired outcomes in visual scenes. In our study, we introduce VSP, a benchmark that 1) evaluates the spatial planning capability in these models in general, and 2) breaks down the visual planning task into finer-grained sub-tasks, including perception and reasoning, and measure the LMs capabilities in these sub-tasks. Our evaluation shows that both open-source and private VLMs fail to generate effective plans for even simple spatial planning tasks. Evaluations on the fine-grained analytical tasks further reveal fundamental deficiencies in the models' visual perception and bottlenecks in reasoning abilities, explaining their worse performance in the general spatial planning tasks. Our work illuminates future directions for improving VLMs' abilities in spatial planning. Our benchmark is publicly available at https://github.com/UCSB-NLP-Chang/Visual-Spatial-Planning.

We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recognition tasks with increasingly long visual contexts composed of both in-distribution and out-of-distribution distractor images. Across these tasks, a diverse set of VLMs rapidly lose performance as the visual context length grows, often exhibiting a striking logarithmic decay trend. This test assesses how well VLMs can ignore irrelevant information when answering queries -- a task that is quite easy for language models (LMs) in the text domain -- demonstrating that current state-of-the-art VLMs lack this essential capability for many long-context applications., Comment: Findings of EMNLP 2024

Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move beyond evaluating simple actions and argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, and robust evaluation metrics. The prompts articulate the initial and final states of scenes, effectively reducing ambiguities for frame development and simplifying the assessment of transition completion. In addition, by collecting aligned real-world videos corresponding to the prompts, we expand TC-Bench's applicability from text-conditional models to image-conditional ones that can perform generative frame interpolation. We also develop new metrics to measure the completeness of component transitions in generated videos, which demonstrate significantly higher correlations with human judgments than existing metrics. Our comprehensive experimental results reveal that most video generators achieve less than 20% of the compositional changes, highlighting enormous space for future improvement. Our analysis indicates that current video generation models struggle to interpret descriptions of compositional changes and synthesize various components across different time steps.

With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness -- the semantic coherence of generated images to the prompts they were conditioned on. A variety of T2I faithfulness metrics have been proposed, leveraging advances in cross-modal embeddings and vision-language models (VLMs). However, these metrics are not rigorously compared and benchmarked, instead presented with correlation to human Likert scores over a set of easy-to-discriminate images against seemingly weak baselines. We introduce T2IScoreScore, a curated set of semantic error graphs containing a prompt and a set of increasingly erroneous images. These allow us to rigorously judge whether a given prompt faithfulness metric can correctly order images with respect to their objective error count and significantly discriminate between different error nodes, using meta-metric scores derived from established statistical tests. Surprisingly, we find that the state-of-the-art VLM-based metrics (e.g., TIFA, DSG, LLMScore, VIEScore) we tested fail to significantly outperform simple (and supposedly worse) feature-based metrics like CLIPScore, particularly on a hard subset of naturally-occurring T2I model errors. TS2 will enable the development of better T2I prompt faithfulness metrics through more rigorous comparison of their conformity to expected orderings and separations under objective criteria., Comment: NeurIPS 2024 Spotlight

The past decades have witnessed the development of new X-ray beam sources with brightness growing at a rate surpassing Moore's law. Current and upcoming diffraction limited and fully coherent X-ray beam sources, including multi-bend achromat based synchrotron sources and high repetition rate X-ray free electron lasers, puts increasingly stringent requirements on stability and accuracy of X-ray optics systems. Parasitic motion errors at sub-micro radian scale in beam transport and beam conditioning optics can lead to significant loss of coherence and brightness delivered from source to experiment. To address this challenge, we incorporated optical metrology based on interferometry and differential wavefront sensing as part of the X-ray optics motion control system. A prototype X-ray optics system was constructed following the optical layout of a tunable X-ray cavity. On-line interferometric metrology enabled dynamical feedback to a motion control system to track and compensate for motion errors. The system achieved sub-microradian scale performance, as multiple optical elements are synchronously and continuously adjusted. This first proof of principle measurement demonstrated both the potential and necessity of incorporating optical metrology as part of the motion control architecture for large scale X-ray optical systems such as monochromators, delay lines, and in particular, X-ray cavity systems to enable the next generation cavity-based X-ray free electron lasers.

Benchmarks of the multilingual capabilities of text-to-image (T2I) models compare generated images prompted in a test language to an expected image distribution over a concept set. One such benchmark, "Conceptual Coverage Across Languages" (CoCo-CroLa), assesses the tangible noun inventory of T2I models by prompting them to generate pictures from a concept list translated to seven languages and comparing the output image populations. Unfortunately, we find that this benchmark contains translation errors of varying severity in Spanish, Japanese, and Chinese. We provide corrections for these errors and analyze how impactful they are on the utility and validity of CoCo-CroLa as a benchmark. We reassess multiple baseline T2I models with the revisions, compare the outputs elicited under the new translations to those conditioned on the old, and show that a correction's impactfulness on the image-domain benchmark results can be predicted in the text domain with similarity scores. Our findings will guide the future development of T2I multilinguality metrics by providing analytical tools for practical translation decisions., Comment: NAACL 2024 Main Conference

Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback. This paper presents a comprehensive review of this emerging class of techniques. We analyze and taxonomize a wide array of recent work utilizing these strategies, including training-time, generation-time, and post-hoc correction. We also summarize the major applications of this strategy and conclude by discussing future directions and challenges., Comment: Work in Progress. Version 2

We propose "Conceptual Coverage Across Languages" (CoCo-CroLa), a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language. This technique allows us to estimate how well-suited a model is to a target language as well as identify model-specific weaknesses, spurious correlations, and biases without a-priori assumptions. We demonstrate how it can be used to benchmark T2I models in terms of multilinguality, and how despite its simplicity it is a good proxy for impressive generalization., Comment: ACL 2023 main conference; 16 pages, 13 figures

Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging the power and robustness of vision-language while alleviating the computational complexities of processing videos. To evaluate this novel application, we introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. Inspired by visually descriptive scene plays, we propose two formats for keyframe description: unstructured dense captions and structured scene descriptions that identify the focus, action, mood, objects, and setting (FAMOuS) of the keyframe. To evaluate video reasoning, we propose two tasks: Video Infilling and Video Prediction, which test abilities to generate multiple intermediate keyframes and predict future keyframes, respectively. We benchmark GPT-4, GPT-3, and VICUNA on VIP, demonstrate the performance gap in these complex video reasoning tasks, and encourage future work to prioritize language models for efficient and generalized video reasoning., Comment: Accepted to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

Voice conversion (VC) models have demonstrated impressive few-shot conversion quality on the clean, native speech populations they're trained on. However, when source or target speech accents, background noise conditions, or microphone characteristics differ from training, quality voice conversion is not guaranteed. These problems are often left unexamined in VC research, giving rise to frustration in users trying to use pretrained VC models on their own data. We are interested in accent-preserving voice conversion for name pronunciation from self-recorded examples, a domain in which all three of the aforementioned conditions are present, and posit that demonstrating higher performance in this domain correlates with creating VC models that are more usable by otherwise frustrated users. We demonstrate that existing SOTA encoder-decoder VC models can be made robust to these variations and endowed with natural denoising capabilities using more diverse data and simple data augmentation techniques in pretraining., Comment: Interspeech 2023 Show and Tell, 2 pp

Recent advances in large language models elicit reasoning in a chain-of-thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves multi-step reasoning ability in language models, it is limited by being unimodal and applied mainly to question-answering tasks. We claim that incorporating visual augmentation into reasoning is essential, especially for complex, imaginative tasks. Consequently, we introduce VCoT, a novel method that leverages chain-of-thought prompting with vision-language grounding to recursively bridge the logical gaps within sequential data. Our method uses visual guidance to generate synthetic multimodal infillings that add consistent and novel information to reduce the logical gaps for downstream tasks that can benefit from temporal reasoning, as well as provide interpretability into models' multi-step reasoning. We apply VCoT to the Visual Storytelling and WikiHow summarization datasets and demonstrate through human evaluation that VCoT offers novel and consistent synthetic data augmentation beating chain-of-thought baselines, which can be used to enhance downstream performance.

Despite widespread calls for transparent artificial intelligence systems, the term is too overburdened with disparate meanings to express precise policy aims or to orient concrete lines of research. Consequently, stakeholders often talk past each other, with policymakers expressing vague demands and practitioners devising solutions that may not address the underlying concerns. Part of why this happens is that a clear ideal of AI transparency goes unsaid in this body of work. We explicitly name such a north star -- transparency that is user-centered, user-appropriate, and honest. We conduct a broad literature survey, identifying many clusters of similar conceptions of transparency, tying each back to our north star with analysis of how it furthers or hinders our ideal AI transparency goals. We conclude with a discussion on common threads across all the clusters, to provide clearer common language whereby policymakers, stakeholders, and practitioners can communicate concrete demands and deliver appropriate solutions. We hope for future work on AI transparency that further advances confident, user-beneficial goals and provides clarity to regulators and developers alike., Comment: 9 pages, 3 tables

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the sensitivity of this capability to the selection of few-shot demonstrations. Current understandings of the underlying mechanisms by which this capability arises from regular language model pretraining objectives remain disconnected from the real-world LLMs. This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models. On this premise, we propose an algorithm to select optimal demonstrations from a set of annotated data with a small LM, and then directly generalize the selected demonstrations to larger LMs. We demonstrate significant improvement over baselines, averaged over eight GPT models on eight real-world text classification datasets. We also demonstrate the real-world usefulness of our algorithm on GSM8K, a math word problem dataset. Our empirical findings support our hypothesis that LLMs implicitly infer a latent variable containing task information., Comment: code at: https://github.com/WANGXinyiLinda/concept-based-demonstration-selection Accepted to NeurIPS 2023

Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. Our analysis reveals that traditional loss functions struggle to effectively incorporate the DAG structure, leading us to propose a causality-enhanced method called Exponential Maximum Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models. To evaluate the needs of considering causality in dialogue generation, we built a comprehensive benchmark on CausalDialogue dataset using different models, inference, and training methods. Through experiments, we find that a causality-inspired loss like ExMATE can improve the diversity and agility of conventional loss function and there is still room for improvement to reach human-level quality on this new dataset., Comment: Accepted to ACL-Findings 2023

As large language models (LLMs) grow larger and more sophisticated, assessing their "reasoning" capabilities in natural language grows more challenging. Recent question answering (QA) benchmarks that attempt to assess reasoning are often limited by a narrow scope of covered situations and subject matters. We introduce WikiWhy, a QA dataset built around a novel auxiliary task: explaining why an answer is true in natural language. WikiWhy contains over 9,000 "why" question-answer-rationale triples, grounded on Wikipedia facts across a diverse set of topics. Each rationale is a set of supporting statements connecting the question to the answer. WikiWhy serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit rationales for each answer to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to be easily memorized. GPT-3 baselines achieve only 38.7% human-evaluated correctness in the end-to-end answer & explain condition, leaving significant room for future improvements.

Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to tasks where large human rating data is already available. We introduce SESCORE, a model-based metric that is highly correlated with human judgements without requiring human annotation, by utilizing a novel, iterative error synthesis and severity scoring pipeline. This pipeline applies a series of plausible errors to raw text and assigns severity labels by simulating human judgements with entailment. We evaluate SESCORE against existing metrics by comparing how their scores correlate with human ratings. SESCORE outperforms all prior unsupervised metrics on multiple diverse NLG tasks including machine translation, image captioning, and WebNLG text generation. For WMT 20/21 En-De and Zh-En, SESCORE improve the average Kendall correlation with human judgement from 0.154 to 0.195. SESCORE even achieves comparable performance to the best supervised metric COMET, despite receiving no human-annotated training data., Comment: EMNLP2022

While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. We also provide an identifiability guarantee of the latent variable model of the proposed data generation process, when utilizing enough train environments. Experiments are conducted on DomainBed, demonstrating empirically that our method obtains the best performance across 20 baselines reported on the benchmark., Comment: Published at ICLR 2023