In an era characterized by the pervasive integration of artificial intelligence into decision-making processes across diverse industries, the demand for trust has never been more pronounced. This thesis embarks on a comprehensive exploration of bias and fairness, with a particular emphasis on their ramifications within the banking sector, where AI-driven decisions bear substantial societal consequences. In this context, the seamless integration of fairness, explainability, and human oversight is of utmost importance, culminating in the establishment of what is commonly referred to as "Responsible AI". This emphasizes the critical nature of addressing biases within the development of a corporate culture that aligns seamlessly with both AI regulations and universal human rights standards, particularly in the realm of automated decision-making systems. Nowadays, embedding ethical principles into the development, training, and deployment of AI models is crucial for compliance with forthcoming European regulations and for promoting societal good. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. These contributions are validated through their practical application in real-world scenarios, in collaboration with Intesa Sanpaolo. This collaborative effort not only contributes to our understanding of fairness but also provides practical tools for the responsible implementation of AI-based decision-making systems. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages, further promoting progress in the field of AI fairness.
相關內容
The growing integration of large language models (LLMs) into social operations amplifies their impact on decisions in crucial areas such as economics, law, education, and healthcare, raising public concerns about these models' discrimination-related safety and reliability. However, prior discrimination measuring frameworks solely assess the average discriminatory behavior of LLMs, often proving inadequate due to the overlook of an additional discrimination-leading factor, i.e., the LLMs' prediction variation across diverse contexts. In this work, we present the Prejudice-Caprice Framework (PCF) that comprehensively measures discrimination in LLMs by considering both their consistently biased preference and preference variation across diverse contexts. Specifically, we mathematically dissect the aggregated contextualized discrimination risk of LLMs into prejudice risk, originating from LLMs' persistent prejudice, and caprice risk, stemming from their generation inconsistency. In addition, we utilize a data-mining approach to gather preference-detecting probes from sentence skeletons, devoid of attribute indications, to approximate LLMs' applied contexts. While initially intended for assessing discrimination in LLMs, our proposed PCF facilitates the comprehensive and flexible measurement of any inductive biases, including knowledge alongside prejudice, across various modality models. We apply our discrimination-measuring framework to 12 common LLMs, yielding intriguing findings: i) modern LLMs demonstrate significant pro-male stereotypes, ii) LLMs' exhibited discrimination correlates with several social and economic factors, iii) prejudice risk dominates the overall discrimination risk and follows a normal distribution, and iv) caprice risk contributes minimally to the overall risk but follows a fat-tailed distribution, suggesting that it is wild risk requiring enhanced surveillance.
Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with specific designed data or inferencing with external knowledge from other sources, incurring inevitable additional costs. In this paper, we present OPERA, a novel MLLM decoding method grounded in an Over-trust Penalty and a Retrospection-Allocation strategy, serving as a nearly free lunch to alleviate the hallucination issue without additional data, knowledge, or training. Our approach begins with an interesting observation that, most hallucinations are closely tied to the knowledge aggregation patterns manifested in the self-attention matrix, i.e., MLLMs tend to generate new tokens by focusing on a few summary tokens, but not all the previous tokens. Such partial over-trust inclination results in the neglecting of image tokens and describes the image content with hallucination. Based on the observation, OPERA introduces a penalty term on the model logits during the beam-search decoding to mitigate the over-trust issue, along with a rollback strategy that retrospects the presence of summary tokens in the previously generated tokens, and re-allocate the token selection if necessary. With extensive experiments, OPERA shows significant hallucination-mitigating performance on different MLLMs and metrics, proving its effectiveness and generality. Our code is available at: //github.com/shikiw/OPERA.
Processing-using-DRAM (PuD) is an emerging paradigm that leverages the analog operational properties of DRAM circuitry to enable massively parallel in-DRAM computation. PuD has the potential to significantly reduce or eliminate costly data movement between processing elements and main memory. Prior works experimentally demonstrate three-input MAJ (i.e., MAJ3) and two-input AND and OR operations in commercial off-the-shelf (COTS) DRAM chips. Yet, demonstrations on COTS DRAM chips do not provide a functionally complete set of operations (e.g., NAND or AND and NOT). We experimentally demonstrate that COTS DRAM chips are capable of performing 1) functionally-complete Boolean operations: NOT, NAND, and NOR and 2) many-input (i.e., more than two-input) AND and OR operations. We present an extensive characterization of new bulk bitwise operations in 256 off-the-shelf modern DDR4 DRAM chips. We evaluate the reliability of these operations using a metric called success rate: the fraction of correctly performed bitwise operations. Among our 19 new observations, we highlight four major results. First, we can perform the NOT operation on COTS DRAM chips with a 98.37% success rate on average. Second, we can perform up to 16-input NAND, NOR, AND, and OR operations on COTS DRAM chips with high reliability (e.g., 16-input NAND, NOR, AND, and OR with an average success rate of 94.94%, 95.87%, 94.94%, and 95.85%, respectively). Third, data pattern only slightly affects bitwise operations. Our results show that executing NAND, NOR, AND, and OR operations with random data patterns decreases the success rate compared to all logic-1/logic-0 patterns by 1.39%, 1.97%, 1.43%, and 1.98%, respectively. Fourth, bitwise operations are highly resilient to temperature changes, with small success rate fluctuations of at most 1.66% among all the tested operations when the temperature is increased from 50C to 95C.
We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessing the capabilities of these LLMs has become a challenging and critical issue due to potential data contamination, and it wastes dozens of time and effort for researchers and engineers to download and try those contaminated models. To save our precious time, we propose a novel and useful method, Clean-Eval, which mitigates the issue of data contamination and evaluates the LLMs in a cleaner manner. Clean-Eval employs an LLM to paraphrase and back-translate the contaminated data into a candidate set, generating expressions with the same meaning but in different surface forms. A semantic detector is then used to filter the generated low-quality samples to narrow down this candidate set. The best candidate is finally selected from this set based on the BLEURT score. According to human assessment, this best candidate is semantically similar to the original contamination data but expressed differently. All candidates can form a new benchmark to evaluate the model. Our experiments illustrate that Clean-Eval substantially restores the actual evaluation results on contaminated LLMs under both few-shot learning and fine-tuning scenarios.
Fairness in artificial intelligence models has gained significantly more attention in recent years, especially in the area of medicine, as fairness in medical models is critical to people's well-being and lives. High-quality medical fairness datasets are needed to promote fairness learning research. Existing medical fairness datasets are all for classification tasks, and no fairness datasets are available for medical segmentation, while medical segmentation is an equally important clinical task as classifications, which can provide detailed spatial information on organ abnormalities ready to be assessed by clinicians. In this paper, we propose the first fairness dataset for medical segmentation named Harvard-FairSeg with 10,000 subject samples. In addition, we propose a fair error-bound scaling approach to reweight the loss function with the upper error-bound in each identity group, using the segment anything model (SAM). We anticipate that the segmentation performance equity can be improved by explicitly tackling the hard cases with high training errors in each identity group. To facilitate fair comparisons, we utilize a novel equity-scaled segmentation performance metric to compare segmentation metrics in the context of fairness, such as the equity-scaled Dice coefficient. Through comprehensive experiments, we demonstrate that our fair error-bound scaling approach either has superior or comparable fairness performance to the state-of-the-art fairness learning models. The dataset and code are publicly accessible via //ophai.hms.harvard.edu/harvard-fairseg10k.
While (large) language models have significantly improved over the last years, they still struggle to sensibly process long sequences found, e.g., in books, due to the quadratic scaling of the underlying attention mechanism. To address this, we propose NextLevelBERT, a Masked Language Model operating not on tokens, but on higher-level semantic representations in the form of text embeddings. We pretrain NextLevelBERT to predict the vector representation of entire masked text chunks and evaluate the effectiveness of the resulting document vectors on three task types: 1) Semantic Textual Similarity via zero-shot document embeddings, 2) Long document classification, 3) Multiple-choice question answering. We find that next level Masked Language Modeling is an effective technique to tackle long-document use cases and can outperform much larger embedding models as long as the required level of detail is not too high. We make model and code available.
To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more complex task in multimodal scenario, which has not been explored in the field of incremental learning. After identifying this stability-plasticity problem when analyzing video with sequential input, we originally propose a method to Mitigate Catastrophic Forgetting in class-incremental learning for multimodal Video Captioning (MCF-VC). As for effectively maintaining good performance on old tasks at the macro level, we design Fine-grained Sensitivity Selection (FgSS) based on the Mask of Linear's Parameters and Fisher Sensitivity to pick useful knowledge from old tasks. Further, in order to better constrain the knowledge characteristics of old and new tasks at the specific feature level, we have created the Two-stage Knowledge Distillation (TsKD), which is able to learn the new task well while weighing the old task. Specifically, we design two distillation losses, which constrain the cross modal semantic information of semantic attention feature map and the textual information of the final outputs respectively, so that the inter-model and intra-model stylized knowledge of the old class is retained while learning the new class. In order to illustrate the ability of our model to resist forgetting, we designed a metric CIDER_t to detect the stage forgetting rate. Our experiments on the public dataset MSR-VTT show that the proposed method significantly resists the forgetting of previous tasks without replaying old samples, and performs well on the new task.
Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among different cognitive processes yield superior outcomes compared to individual cognitive processes in isolation. Although Large Language Models (LLMs) have demonstrated promising performance as general task-solving agents, they still struggle with tasks that require intensive domain knowledge and complex reasoning. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist refers to an intelligent agent that collaborates with multiple minds, combining their individual strengths and knowledge, to enhance problem-solving and overall performance in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. We have discovered that assigning multiple, fine-grained personas in LLMs elicits better problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, SPP effectively elicits internal knowledge acquisition abilities, reduces hallucination, and maintains strong reasoning capabilities. Code, data, and prompts can be found at: //github.com/MikeWangWZHL/Solo-Performance-Prompting.git.
Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking. In recent years, large language models (LLMs) have made significant progress in natural language processing, and there is observation that these models may exhibit reasoning abilities when they are sufficiently large. However, it is not yet clear to what extent LLMs are capable of reasoning. This paper provides a comprehensive overview of the current state of knowledge on reasoning in LLMs, including techniques for improving and eliciting reasoning in these models, methods and benchmarks for evaluating reasoning abilities, findings and implications of previous research in this field, and suggestions on future directions. Our aim is to provide a detailed and up-to-date review of this topic and stimulate meaningful discussion and future work.
Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more on the essential aspects of data. Deep learning has employed attention to boost performance for many applications. Interestingly, the same attention design can suit processing different data modalities and can easily be incorporated into large networks. Furthermore, multiple complementary attention mechanisms can be incorporated in one network. Hence, attention techniques have become extremely attractive. However, the literature lacks a comprehensive survey specific to attention techniques to guide researchers in employing attention in their deep models. Note that, besides being demanding in terms of training data and computational resources, transformers only cover a single category in self-attention out of the many categories available. We fill this gap and provide an in-depth survey of 50 attention techniques categorizing them by their most prominent features. We initiate our discussion by introducing the fundamental concepts behind the success of attention mechanism. Next, we furnish some essentials such as the strengths and limitations of each attention category, describe their fundamental building blocks, basic formulations with primary usage, and applications specifically for computer vision. We also discuss the challenges and open questions related to attention mechanism in general. Finally, we recommend possible future research directions for deep attention.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191