arXiv subjects

Huaxiu Yao

Publications and source records attributed to Huaxiu Yao.

At least 127 records · Page 7Linked to original sources

arXiv2024

$C^3$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding

Cross-lingual natural language understanding (NLU) is a critical task in natural language processing (NLP). Recent advancements have seen multilingual pre-trained language models (mPLMs) significantly enhance the performance of these tasks. However, mPLMs necessitate substantial resources and incur high computational costs during inference, posing challenges for deployment in real-world and real-time systems. Existing model cascade methods seek to enhance inference efficiency by greedily selecting the lightest model capable of processing the current input from a variety of models, based on model confidence scores. Nonetheless, deep models tend to exhibit overconfidence, and confidence distributions vary across languages. This leads to the emission of confident but incorrect predictions by smaller models, hindering their ability to generalize effectively across test languages. In this study, we introduce a confidence calibration model cascade ($C^3$) method. This approach, simple yet effective, involves calibration prior to cascade inference, thereby enhancing cascade accuracy through more reliable predictions. Extensive experiments conducted on three cross-lingual benchmarks demonstrate that $C^3$ significantly outperforms all state-of-the-art baselines.

cs.CL↗

arXiv2024

Aligning Modalities in Vision Large Language Models via Preference Fine-tuning

Instruction-following Vision Large Language Models (VLLMs) have achieved significant progress recently on a variety of tasks. These approaches merge strong pre-trained vision models and large language models (LLMs). Since these components are trained separately, the learned representations need to be aligned with joint training on additional image-language pairs. This procedure is not perfect and can cause the model to hallucinate - provide answers that do not accurately reflect the image, even when the core LLM is highly factual and the vision backbone has sufficiently complete representations. In this work, we frame the hallucination problem as an alignment issue, tackle it with preference tuning. Specifically, we propose POVID to generate feedback data with AI models. We use ground-truth instructions as the preferred response and a two-stage approach to generate dispreferred data. First, we prompt GPT-4V to inject plausible hallucinations into the correct answer. Second, we distort the image to trigger the inherent hallucination behavior of the VLLM. This is an automated approach, which does not rely on human data generation or require a perfect expert, which makes it easily scalable. Finally, both of these generation strategies are integrated into an RLHF pipeline via Direct Preference Optimization. In experiments across broad benchmarks, we show that we can not only reduce hallucinations, but improve model performance across standard benchmarks, outperforming prior approaches. Our data and code are available at https://github.com/YiyangZhou/POVID.

cs.LG↗

arXiv2024

AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition

Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framework AutoPRM that efficiently enhances the fine-tuning of LLMs for intricate reasoning challenges. Specifically, AutoPRM first decomposes complex problems into more manageable subquestions with a controllable granularity switch, then sequentially apply reinforcement learning to iteratively improve the subquestion solver. Additionally, we propose context-guided-decoding to avoid reward tampering and guide the subquestion solver towards the solution of the holistic problem. Extensive experiments show that AutoPRM significantly improves performance on mathematical and commonsense reasoning tasks over SOTA. More encouragingly, AutoPRM can be easily integrated with other orthogonal reasoning pipelines.

cs.CL↗

arXiv2024

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences

Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated. To address this challenge, this paper introduces Mementos, a new benchmark designed to assess MLLMs' sequential image reasoning abilities. Mementos features 4,761 diverse image sequences with varying lengths. We also employ a GPT-4 assisted method to evaluate MLLM reasoning performance. Through a careful evaluation of nine recent MLLMs on Mementos, including GPT-4V and Gemini, we find that they struggle to accurately describe dynamic information about given image sequences, often leading to hallucinations/misrepresentations of objects and their corresponding behaviors. Our quantitative analysis and case studies identify three key factors impacting MLLMs' sequential image reasoning: the correlation between object and behavioral hallucinations, the influence of cooccurring behaviors, and the compounding impact of behavioral hallucinations. Our dataset is available at https://github.com/umd-huang-lab/Mementos.

cs.CV↗

arXiv2023

How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs

This work focuses on the potential of Vision LLMs (VLLMs) in visual reasoning. Different from prior studies, we shift our focus from evaluating standard performance to introducing a comprehensive safety evaluation suite, covering both out-of-distribution (OOD) generalization and adversarial robustness. For the OOD evaluation, we present two novel VQA datasets, each with one variant, designed to test model performance under challenging conditions. In exploring adversarial robustness, we propose a straightforward attack strategy for misleading VLLMs to produce visual-unrelated responses. Moreover, we assess the efficacy of two jailbreaking strategies, targeting either the vision or language component of VLLMs. Our evaluation of 21 diverse models, ranging from open-source VLLMs to GPT-4V, yields interesting observations: 1) Current VLLMs struggle with OOD texts but not images, unless the visual information is limited; and 2) These VLLMs can be easily misled by deceiving vision encoders only, and their vision-language training often compromise safety protocols. We release this safety evaluation suite at https://github.com/UCSC-VLAA/vllm-safety-benchmark.

cs.CV↗

arXiv2023

Fine-tuning Language Models for Factuality

The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations.' These errors can inadvertently spread misinformation or harmfully perpetuate misconceptions. Further, manual fact-checking of model responses is a time-consuming process, making human factuality labels expensive to acquire. In this work, we fine-tune language models to be more factual, without human labeling and targeting more open-ended generation settings than past work. We leverage two key recent innovations in NLP to do so. First, several recent works have proposed methods for judging the factuality of open-ended text by measuring consistency with an external knowledge base or simply a large model's confidence scores. Second, the direct preference optimization algorithm enables straightforward fine-tuning of language models on objectives other than supervised imitation, using a preference ranking over possible model responses. We show that learning from automatically generated factuality preference rankings, generated either through existing retrieval systems or our novel retrieval-free approach, significantly improves the factuality (percent of generated claims that are correct) of Llama-2 on held-out topics compared with RLHF or decoding strategies targeted at factuality. At 7B scale, compared to Llama-2-chat, we observe 58% and 40% reduction in factual error rate when generating biographies and answering medical questions, respectively.

cs.CL↗

arXiv2023

Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges

While GPT-4V(ision) impressively models both visual and textual information simultaneously, it's hallucination behavior has not been systematically assessed. To bridge this gap, we introduce a new benchmark, namely, the Bias and Interference Challenges in Visual Language Models (Bingo). This benchmark is designed to evaluate and shed light on the two common types of hallucinations in visual language models: bias and interference. Here, bias refers to the model's tendency to hallucinate certain types of responses, possibly due to imbalance in its training data. Interference pertains to scenarios where the judgment of GPT-4V(ision) can be disrupted due to how the text prompt is phrased or how the input image is presented. We identify a notable regional bias, whereby GPT-4V(ision) is better at interpreting Western images or images with English writing compared to images from other countries or containing text in other languages. Moreover, GPT-4V(ision) is vulnerable to leading questions and is often confused when interpreting multiple images together. Popular mitigation approaches, such as self-correction and chain-of-thought reasoning, are not effective in resolving these challenges. We also identified similar biases and interference vulnerabilities with LLaVA and Bard. Our results characterize the hallucination challenges in GPT-4V(ision) and state-of-the-art visual-language models, and highlight the need for new solutions. The Bingo benchmark is available at https://github.com/gzcch/Bingo.

cs.LG↗

arXiv2023

Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback

A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the answer is correct, enabling deferral to an expert in cases of low-confidence predictions. Recent studies have shown that unsupervised pre-training produces large language models (LMs) whose conditional probabilities are remarkably well-calibrated. However, the most widely-used LMs are fine-tuned with reinforcement learning from human feedback (RLHF-LMs), and some studies have suggested that RLHF-LMs produce conditional probabilities that are very poorly calibrated. In light of this perceived weakness, we conduct a broad evaluation of methods for extracting confidence scores from RLHF-LMs. For RLHF-LMs such as ChatGPT, GPT-4, and Claude, we find that verbalized confidences emitted as output tokens are typically better-calibrated than the model's conditional probabilities on the TriviaQA, SciQ, and TruthfulQA benchmarks, often reducing the expected calibration error by a relative 50%.

cs.CL↗

arXiv2023

Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations

There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. Current methods for addressing this problem only consider scenarios where all examples come from the same distribution. However, in many cases, there are multiple domains with distinct class imbalance. We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains. Towards that goal, we introduce TALLY, a method that addresses this multi-domain long-tailed learning problem. Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another, producing a new representation for use as data augmentation. To improve the disentanglement of semantic representations, TALLY further utilizes a domain-invariant class prototype that averages out domain-specific effects. We evaluate TALLY on several benchmarks and real-world datasets and find that it consistently outperforms other state-of-the-art methods in both subpopulation and domain shift. Our code and data have been released at https://github.com/huaxiuyao/TALLY.

cs.LG↗

arXiv2023

Holistic Evaluation of Language Models

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios when possible (87.5% of the time). This ensures metrics beyond accuracy don't fall to the wayside, and that trade-offs are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to analyze specific aspects (e.g. reasoning, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, 21 of which were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on the same core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings. For full transparency, we release all raw model prompts and completions publicly for further analysis, as well as a general modular toolkit. We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

cs.CL↗

arXiv2023

Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks

As machine learning has been deployed ubiquitously across applications in modern data science, algorithmic fairness has become a great concern. Among them, imposing fairness constraints during learning, i.e. in-processing fair training, has been a popular type of training method because they don't require accessing sensitive attributes during test time in contrast to post-processing methods. While this has been extensively studied in classical machine learning models, their impact on deep neural networks remains unclear. Recent research has shown that adding fairness constraints to the objective function leads to severe over-fitting to fairness criteria in large models, and how to solve this challenge is an important open question. To tackle this, we leverage the wisdom and power of pre-training and fine-tuning and develop a simple but novel framework to train fair neural networks in an efficient and inexpensive way -- last-layer fine-tuning alone can effectively promote fairness in deep neural networks. This framework offers valuable insights into representation learning for training fair neural networks.

cs.LG↗

arXiv2023

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task. This paper shows that in such settings, selectively fine-tuning a subset of layers (which we term surgical fine-tuning) matches or outperforms commonly used fine-tuning approaches. Moreover, the type of distribution shift influences which subset is more effective to tune: for example, for image corruptions, fine-tuning only the first few layers works best. We validate our findings systematically across seven real-world data tasks spanning three types of distribution shifts. Theoretically, we prove that for two-layer neural networks in an idealized setting, first-layer tuning can outperform fine-tuning all layers. Intuitively, fine-tuning more parameters on a small target dataset can cause information learned during pre-training to be forgotten, and the relevant information depends on the type of shift.

cs.LG↗

arXiv2023

Diversify and Disambiguate: Learning From Underspecified Data

Many datasets are underspecified: there exist multiple equally viable solutions to a given task. Underspecification can be problematic for methods that learn a single hypothesis because different functions that achieve low training loss can focus on different predictive features and thus produce widely varying predictions on out-of-distribution data. We propose DivDis, a simple two-stage framework that first learns a diverse collection of hypotheses for a task by leveraging unlabeled data from the test distribution. We then disambiguate by selecting one of the discovered hypotheses using minimal additional supervision, in the form of additional labels or inspection of function visualization. We demonstrate the ability of DivDis to find hypotheses that use robust features in image classification and natural language processing problems with underspecification.

cs.LG↗

arXiv2023

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

Distribution shift occurs when the test distribution differs from the training distribution, and it can considerably degrade performance of machine learning models deployed in the real world. Temporal shifts -- distribution shifts arising from the passage of time -- often occur gradually and have the additional structure of timestamp metadata. By leveraging timestamp metadata, models can potentially learn from trends in past distribution shifts and extrapolate into the future. While recent works have studied distribution shifts, temporal shifts remain underexplored. To address this gap, we curate Wild-Time, a benchmark of 5 datasets that reflect temporal distribution shifts arising in a variety of real-world applications, including patient prognosis and news classification. On these datasets, we systematically benchmark 13 prior approaches, including methods in domain generalization, continual learning, self-supervised learning, and ensemble learning. We use two evaluation strategies: evaluation with a fixed time split (Eval-Fix) and evaluation with a data stream (Eval-Stream). Eval-Fix, our primary evaluation strategy, aims to provide a simple evaluation protocol, while Eval-Stream is more realistic for certain real-world applications. Under both evaluation strategies, we observe an average performance drop of 20% from in-distribution to out-of-distribution data. Existing methods are unable to close this gap. Code is available at https://wild-time.github.io/.

cs.LG↗

arXiv2022

Knowledge-Driven New Drug Recommendation

Drug recommendation assists doctors in prescribing personalized medications to patients based on their health conditions. Existing drug recommendation solutions adopt the supervised multi-label classification setup and only work with existing drugs with sufficient prescription data from many patients. However, newly approved drugs do not have much historical prescription data and cannot leverage existing drug recommendation methods. To address this, we formulate the new drug recommendation as a few-shot learning problem. Yet, directly applying existing few-shot learning algorithms faces two challenges: (1) complex relations among diseases and drugs and (2) numerous false-negative patients who were eligible but did not yet use the new drugs. To tackle these challenges, we propose EDGE, which can quickly adapt to the recommendation for a new drug with limited prescription data from a few support patients. EDGE maintains a drug-dependent multi-phenotype few-shot learner to bridge the gap between existing and new drugs. Specifically, EDGE leverages the drug ontology to link new drugs to existing drugs with similar treatment effects and learns ontology-based drug representations. Such drug representations are used to customize the metric space of the phenotype-driven patient representations, which are composed of a set of phenotypes capturing complex patient health status. Lastly, EDGE eliminates the false-negative supervision signal using an external drug-disease knowledge base. We evaluate EDGE on two real-world datasets: the public EHR data (MIMIC-IV) and private industrial claims data. Results show that EDGE achieves 7.3% improvement on the ROC-AUC score over the best baseline.

cs.LG↗

arXiv2022

C-Mixup: Improving Generalization in Regression

Improving the generalization of deep networks is an important open challenge, particularly in domains without plentiful data. The mixup algorithm improves generalization by linearly interpolating a pair of examples and their corresponding labels. These interpolated examples augment the original training set. Mixup has shown promising results in various classification tasks, but systematic analysis of mixup in regression remains underexplored. Using mixup directly on regression labels can result in arbitrarily incorrect labels. In this paper, we propose a simple yet powerful algorithm, C-Mixup, to improve generalization on regression tasks. In contrast with vanilla mixup, which picks training examples for mixing with uniform probability, C-Mixup adjusts the sampling probability based on the similarity of the labels. Our theoretical analysis confirms that C-Mixup with label similarity obtains a smaller mean square error in supervised regression and meta-regression than vanilla mixup and using feature similarity. Another benefit of C-Mixup is that it can improve out-of-distribution robustness, where the test distribution is different from the training distribution. By selectively interpolating examples with similar labels, it mitigates the effects of domain-associated information and yields domain-invariant representations. We evaluate C-Mixup on eleven datasets, ranging from tabular to video data. Compared to the best prior approach, C-Mixup achieves 6.56%, 4.76%, 5.82% improvements in in-distribution generalization, task generalization, and out-of-distribution robustness, respectively. Code is released at https://github.com/huaxiuyao/C-Mixup.

cs.LG↗

arXiv2022

Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation

Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available. Optimization-based meta-learning algorithms achieve promising results in low-resource scenarios by adapting a well-generalized model initialization to handle new tasks. Nonetheless, these approaches suffer from the memorization overfitting issue, where the model tends to memorize the meta-training tasks while ignoring support sets when adapting to new tasks. To address this issue, we propose a memory imitation meta-learning (MemIML) method that enhances the model's reliance on support sets for task adaptation. Specifically, we introduce a task-specific memory module to store support set information and construct an imitation module to force query sets to imitate the behaviors of some representative support-set samples stored in the memory. A theoretical analysis is provided to prove the effectiveness of our method, and empirical results also demonstrate that our method outperforms competitive baselines on both text classification and generation tasks.

cs.CL↗

arXiv2022

Improving Out-of-Distribution Robustness via Selective Augmentation

Machine learning algorithms typically assume that training and test examples are drawn from the same distribution. However, distribution shift is a common problem in real-world applications and can cause models to perform dramatically worse at test time. In this paper, we specifically consider the problems of subpopulation shifts (e.g., imbalanced data) and domain shifts. While prior works often seek to explicitly regularize internal representations or predictors of the model to be domain invariant, we instead aim to learn invariant predictors without restricting the model's internal representations or predictors. This leads to a simple mixup-based technique which learns invariant predictors via selective augmentation called LISA. LISA selectively interpolates samples either with the same labels but different domains or with the same domain but different labels. Empirically, we study the effectiveness of LISA on nine benchmarks ranging from subpopulation shifts to domain shifts, and we find that LISA consistently outperforms other state-of-the-art methods and leads to more invariant predictors. We further analyze a linear setting and theoretically show how LISA leads to a smaller worst-group error.

cs.LG↗