Foundational Models (FMs) are gaining increasing attention in the biomedical AI ecosystem due to their ability to represent and contextualize multimodal biomedical data. These capabilities make FMs a valuable tool for a variety of tasks, including biomedical reasoning, hypothesis generation, and interpreting complex imaging data. In this review paper, we address the unique challenges associated with establishing an ethical and trustworthy biomedical AI ecosystem, with a particular focus on the development of FMs and their downstream applications. We explore strategies that can be implemented throughout the biomedical AI pipeline to effectively tackle these challenges, ensuring that these FMs are translated responsibly into clinical and translational settings. Additionally, we emphasize the importance of key stewardship and co-design principles that not only ensure robust regulation but also guarantee that the interests of all stakeholders, especially those involved in or affected by these clinical and translational applications are adequately represented. We aim to empower the biomedical AI community to harness these models responsibly and effectively. As we navigate this exciting frontier, our collective commitment to ethical stewardship, co-design, and responsible translation will be instrumental in ensuring that the evolution of FMs truly enhances patient care and medical decision making, ultimately leading to a more equitable and trustworthy biomedical AI ecosystem.

When the initial vision of Explainable (XAI) was articulated, the most popular framing was to open the (proverbial) "black-box" of AI so that we could understand the inner workings. With the advent of Large Language Models (LLMs), the very ability to open the black-box is increasingly limited especially when it comes to non-AI expert end-users. In this paper, we challenge the assumption of "opening" the black-box in the LLM era and argue for a shift in our XAI expectations. Highlighting the epistemic blind spots of an algorithm-centered XAI view, we argue that a human-centered perspective can be a path forward. We operationalize the argument by synthesizing XAI research along three dimensions: explainability outside the black-box, explainability around the edges of the black box, and explainability that leverages infrastructural seams. We conclude with takeaways that reflexively inform XAI as a domain.

Large language model (LLM) agents have shown great potential in solving realworld software engineering (SWE) problems. The most advanced open-source SWE agent can resolve over 27% of real GitHub issues in SWE-Bench Lite. To fully harness the diversity of these agents, we propose DEI (Diversity Empowered Intelligence), a framework that leverages their unique expertise. DEI functions as a meta-module atop existing SWE agent frameworks, managing agent collectives for enhanced problemsolving. Experimental results show that a DEI-guided committee of agents is able to surpass the best individual agent's performance by a large margin. For instance, a group of open-source SWE agents, with a maximum individual resolve rate of 27.3% on SWE-Bench Lite, can achieve a 34.3% resolve rate with DEI, making a 25% improvement and beating most closed-source solutions. Our findings contribute to the growing body of research on collaborative AI systems and their potential to solve complex software engineering challenges. Recent advancements in large language models (LLMs) have transformed software engineering (SWE) and other domains.

The success of Large Language Models (LLMs) in multicultural environments hinges on their ability to understand users' diverse cultural backgrounds. We measure this capability by having an LLM simulate human profiles representing various nationalities within the scope of a questionnaire-style psychological experiment. Specifically, we employ GPT-3.5 to reproduce reactions to persuasive news articles of 7,286 participants from 15 countries; comparing the results with a dataset of real participants sharing the same demographic traits. Our analysis shows that specifying a person's country of residence improves GPT-3.5's alignment with their responses. In contrast, using native language prompting introduces shifts that significantly reduce overall alignment, with some languages particularly impairing performance. These findings suggest that while direct nationality information enhances the model's cultural adaptability, native language cues do not reliably improve simulation fidelity and can detract from the model's effectiveness.

Future event prediction (FEP) is a long-standing and crucial task in the world, as understanding the evolution of events enables early risk identification, informed decision-making, and strategic planning. Existing work typically treats event prediction as classification tasks and confines the outcomes of future events to a fixed scope, such as yes/no questions, candidate set, and taxonomy, which is difficult to include all possible outcomes of future events. In this paper, we introduce OpenEP (an Open-Ended Future Event Prediction task), which generates flexible and diverse predictions aligned with real-world scenarios. This is mainly reflected in two aspects: firstly, the predictive questions are diverse, covering different stages of event development and perspectives; secondly, the outcomes are flexible, without constraints on scope or format. To facilitate the study of this task, we construct OpenEPBench, an open-ended future event prediction dataset. For question construction, we pose questions from seven perspectives, including location, time, event development, event outcome, event impact, event response, and other, to facilitate an in-depth analysis and understanding of the comprehensive evolution of events. For outcome construction, we collect free-form text containing the outcomes as ground truth to provide semantically complete and detail-enriched outcomes. Furthermore, we propose StkFEP, a stakeholder-enhanced future event prediction framework, that incorporates event characteristics for open-ended settings. Our method extracts stakeholders involved in events to extend questions to gather diverse information. We also collect historically events that are relevant and similar to the question to reveal potential evolutionary patterns. Experiment results indicate that accurately predicting future events in open-ended settings is challenging for existing LLMs.

We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs). Given documents from a web corpus, we generate and curate synthetic instructions using the backtranslation approach proposed by Li et al.(2023a), and rewrite the responses to improve their quality further based on the initial documents. Fine-tuning with the resulting (backtranslated instruction, rewritten response) pairs yields higher win rates on AlpacaEval than using other common instruction datasets such as Humpback, ShareGPT, Open Orca, Alpaca-GPT4 and Self-instruct. We also demonstrate that rewriting the responses with an LLM outperforms direct distillation, and the two generated text distributions exhibit significant distinction in embedding space. Further analysis shows that our backtranslated instructions are of higher quality than other sources of synthetic instructions, while our responses are more diverse and complex than those obtained from distillation. Overall we find that instruction back-and-forth translation combines the best of both worlds -- making use of the information diversity and quantity found on the web, while ensuring the quality of the responses which is necessary for effective alignment.

In this study, we present an innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence. Our system seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations. Leveraging a vector database to achieve retrievable answer generation, our OpenSI AI system elucidates its decision-making process, bridging the gap between raw computation and human-like understanding. Our choice of Chess as the demonstration environment underscores the versatility of our approach. Beyond Chess, our system holds promise for diverse applications, from medical diagnostics to financial forecasting.

The analysis of students' emotions and behaviors is crucial for enhancing learning outcomes and personalizing educational experiences. Traditional methods often rely on intrusive visual and physiological data collection, posing privacy concerns and scalability issues. This paper proposes a novel method leveraging large language models (LLMs) and prompt engineering to analyze textual data from students. Our approach utilizes tailored prompts to guide LLMs in detecting emotional and engagement states, providing a non-intrusive and scalable solution. We conducted experiments using Qwen, ChatGPT, Claude2, and GPT-4, comparing our method against baseline models and chain-of-thought (CoT) prompting. Results demonstrate that our method significantly outperforms the baselines in both accuracy and contextual understanding. This study highlights the potential of LLMs combined with prompt engineering to offer practical and effective tools for educational emotion and behavior analysis.

The deployment of Large Language Models (LLMs) in content generation raises significant safety concerns, particularly regarding the transparency and interpretability of content evaluations. Current methods, primarily focused on binary safety classifications, lack mechanisms for detailed critique, limiting their utility for model improvement and user trust. To address these limitations, we introduce SAFETY-J, a bilingual generative safety evaluator for English and Chinese with critique-based judgment. SAFETY-J utilizes a robust training dataset that includes diverse dialogues and augmented query-response pairs to assess safety across various scenarios comprehensively. We establish an automated meta-evaluation benchmark that objectively assesses the quality of critiques with minimal human intervention, facilitating scalable and continuous improvement. Additionally, SAFETY-J employs an iterative preference learning technique to dynamically refine safety assessments based on meta-evaluations and critiques. Our evaluations demonstrate that SAFETY-J provides more nuanced and accurate safety evaluations, thereby enhancing both critique quality and predictive reliability in complex content scenarios. To facilitate further research and application, we open-source SAFETY-J's training protocols, datasets, and code at https://github.com/GAIR-NLP/Safety-J.

Fine-tuning large language models (LLMs) with high parameter efficiency for downstream tasks has become a new paradigm. Low-Rank Adaptation (LoRA) significantly reduces the number of trainable parameters for fine-tuning. Although it has demonstrated commendable performance, updating parameters within a single scale may not be the optimal choice for complex downstream tasks.In this paper, we extend the LoRA to multiple scales, dubbed as LoRA$^2$. We first combine orthogonal projection theory to train a set of LoRAs in two mutually orthogonal planes. Then, we improve the importance score algorithm, which reduce parameter sensitivity score calculations by approximately 98.5\%. By pruning singular values with lower importance scores, thereby enhancing adaptability to various downstream tasks. Extensive experiments are conducted on two widely used pre-trained models to validate the effectiveness of LoRA$^2$. Results show that it significantly reduces the number of trainable parameters to just 0.72\% compared to full fine-tuning, while still delivering highly impressive performance. Even when the parameters are further reduced to 0.17M, it still achieves comparable results to the baseline with 8 times more parameters. Our code is available here: https://anonymous.4open.science/r/LoRA-2-5B4C