ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain

The advancement and extensive application of large language models (LLMs) have been remarkable, including their use in scientific research assistance. However, these models often generate scientifically incorrect or unsafe responses, and in some cases, they may encourage users to engage in dangerous behavior. To address this issue in the field of chemistry, we introduce ChemSafetyBench, a benchmark designed to evaluate the accuracy and safety of LLM responses. ChemSafetyBench encompasses three key tasks: querying chemical properties, assessing the legality of chemical uses, and describing synthesis methods, each requiring increasingly deeper chemical knowledge. Our dataset has more than 30K samples across various chemical materials. We incorporate handcrafted templates and advanced jailbreaking scenarios to enhance task diversity. Our automated evaluation framework thoroughly assesses the safety, accuracy, and appropriateness of LLM responses. Extensive experiments with state-of-the-art LLMs reveal notable strengths and critical vulnerabilities, underscoring the need for robust safety measures. ChemSafetyBench aims to be a pivotal tool in developing safer AI technologies in chemistry. Our code and dataset are available at https://github.com/HaochenZhao/SafeAgent4Chem. Warning: this paper contains discussions on the synthesis of controlled chemicals using AI models.

Improving Model Factuality with Fine-grained Critique-based Evaluator

Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. We conduct data augmentation on a combination of public judgment datasets to train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools. We then present a framework that leverages FenCE to improve the factuality of LM generators by constructing training data. Specifically, we generate a set of candidate responses, leverage FenCE to revise and score each response without introducing lesser-known facts, and train the generator by preferring highly scored revised responses. Experiments show that our data augmentation methods improve the evaluator's accuracy by 2.9% on LLM-AggreFact. With FenCE, we improve Llama3-8B-chat's factuality rate by 14.45% on FActScore, outperforming state-of-the-art factuality finetuning methods by 6.96%.

Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following

Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs' ability to follow instructions remains challenging due to the complexity and subjectivity of human language. Current benchmarks primarily focus on single-turn, monolingual instructions, which do not adequately reflect the complexities of real-world applications that require handling multi-turn and multilingual interactions. To address this gap, we introduce Multi-IF, a new benchmark designed to assess LLMs' proficiency in following multi-turn and multilingual instructions. Multi-IF, which utilizes a hybrid framework combining LLM and human annotators, expands upon the IFEval by incorporating multi-turn sequences and translating the English prompts into another 7 languages, resulting in a dataset of 4,501 multilingual conversations, where each has three turns. Our evaluation of 14 state-of-the-art LLMs on Multi-IF reveals that it presents a significantly more challenging task than existing benchmarks. All the models tested showed a higher rate of failure in executing instructions correctly with each additional turn. For example, o1-preview drops from 0.877 at the first turn to 0.707 at the third turn in terms of average accuracy over all languages. Moreover, languages with non-Latin scripts (Hindi, Russian, and Chinese) generally exhibit higher error rates, suggesting potential limitations in the models' multilingual capabilities. We release Multi-IF prompts and the evaluation code base to encourage further research in this critical area.

From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues

Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions. Our study systematically analyzes self-anthropomorphic expression within various dialogue datasets, outlining the contrasts between self-anthropomorphic and non-self-anthropomorphic responses in dialogue systems. We show significant differences in these two types of responses and propose transitioning from one type to the other. We also introduce Pix2Persona, a novel dataset aimed at developing ethical and engaging AI systems in various embodiments. This dataset preserves the original dialogues from existing corpora and enhances them with paired responses: self-anthropomorphic and non-self-anthropomorphic for each original bot response. Our work not only uncovers a new category of bot responses that were previously under-explored but also lays the groundwork for future studies about dynamically adjusting self-anthropomorphism levels in AI systems to align with ethical standards and user expectations.

The Perfect Blend: Redefining RLHF with Mixture of Judges

Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM). However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme multi-objective optimization (i.e., trade-off of multiple and/or sometimes conflicting objectives). Applying RLHF for MTL currently requires careful tuning of the weights for reward model and data combinations. This is often done via human intuition and does not generalize. In this work, we introduce a novel post-training paradigm which we called Constrained Generative Policy Optimization (CGPO). The core of CGPO is Mixture of Judges (MoJ) with cost-efficient constrained policy optimization with stratification, which can identify the perfect blend in RLHF in a principled manner. It shows strong empirical results with theoretical guarantees, does not require extensive hyper-parameter tuning, and is plug-and-play in common post-training pipelines. Together, this can detect and mitigate reward hacking behaviors while reaching a pareto-optimal point across an extremely large number of objectives. Our empirical evaluations demonstrate that CGPO significantly outperforms standard RLHF algorithms like PPO and DPO across various tasks including general chat, STEM questions, instruction following, and coding. Specifically, CGPO shows improvements of 7.4% in AlpacaEval-2 (general chat), 12.5% in Arena-Hard (STEM & reasoning), and consistent gains in other domains like math and coding. Notably, PPO, while commonly used, is prone to severe reward hacking in popular coding benchmarks, which CGPO successfully addresses. This breakthrough in RLHF not only tackles reward hacking and extreme multi-objective optimization challenges but also advances the state-of-the-art in aligning general-purpose LLMs for diverse applications.

InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting

Transformer has become one of the most popular architectures for multivariate time series (MTS) forecasting. Recent Transformer-based MTS models generally prefer channel-independent structures with the observation that channel independence can alleviate noise and distribution drift issues, leading to more robustness. Nevertheless, it is essential to note that channel dependency remains an inherent characteristic of MTS, carrying valuable information. Designing a model that incorporates merits of both channel-independent and channel-mixing structures is a key to further improvement of MTS forecasting, which poses a challenging conundrum. To address the problem, an injection method for global information into channel-independent Transformer, InjectTST, is proposed in this paper. Instead of designing a channel-mixing model directly, we retain the channel-independent backbone and gradually inject global information into individual channels in a selective way. A channel identifier, a global mixing module and a self-contextual attention module are devised in InjectTST. The channel identifier can help Transformer distinguish channels for better representation. The global mixing module produces cross-channel global information. Through the self-contextual attention module, the independent channels can selectively concentrate on useful global information without robustness degradation, and channel mixing is achieved implicitly. Experiments indicate that InjectTST can achieve stable improvement compared with state-of-the-art models.

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning

Despite vision-language models' (VLMs) remarkable capabilities as versatile visual assistants, two substantial challenges persist within the existing VLM frameworks: (1) lacking task diversity in pretraining and visual instruction tuning, and (2) annotation error and bias in GPT-4 synthesized instruction tuning data. Both challenges lead to issues such as poor generalizability, hallucination, and catastrophic forgetting. To address these challenges, we construct Vision-Flan, the most diverse publicly available visual instruction tuning dataset to date, comprising 187 diverse tasks and 1,664,261 instances sourced from academic datasets, and each task is accompanied by an expert-written instruction. In addition, we propose a two-stage instruction tuning framework, in which VLMs are firstly finetuned on Vision-Flan and further tuned on GPT-4 synthesized data. We find this two-stage tuning framework significantly outperforms the traditional single-stage visual instruction tuning framework and achieves the state-of-the-art performance across a wide range of multi-modal evaluation benchmarks. Finally, we conduct in-depth analyses to understand visual instruction tuning and our findings reveal that: (1) GPT-4 synthesized data does not substantially enhance VLMs' capabilities but rather modulates the model's responses to human-preferred formats; (2) A minimal quantity (e.g., 1,000) of GPT-4 synthesized data can effectively align VLM responses with human-preference; (3) Visual instruction tuning mainly helps large-language models (LLMs) to understand visual features.

GOODAT: Towards Test-time Graph Out-of-Distribution Detection

Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. While GNNs excel in scenarios where the testing data shares the distribution of their training counterparts (in distribution, ID), they often exhibit incorrect predictions when confronted with samples from an unfamiliar distribution (out-of-distribution, OOD). To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN. Despite their effectiveness, these methods come with heavy training resources and costs, as they need to optimize the GNN-based models on training data. Moreover, their reliance on modifying the original GNNs and accessing training data further restricts their universality. To this end, this paper introduces a method to detect Graph Out-of-Distribution At Test-time (namely GOODAT), a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture. With a lightweight graph masker, GOODAT can learn informative subgraphs from test samples, enabling the capture of distinct graph patterns between OOD and ID samples. To optimize the graph masker, we meticulously design three unsupervised objective functions based on the graph information bottleneck principle, motivating the masker to capture compact yet informative subgraphs for OOD detection. Comprehensive evaluations confirm that our GOODAT method outperforms state-of-the-art benchmarks across a variety of real-world datasets. The code is available at Github: https://github.com/Ee1s/GOODAT

Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of ranking of response pairs to perform this alignment. However, human preference on LLM outputs can come in much richer forms including natural language, which may provide detailed feedback on strengths and weaknesses of a given response. In this work we investigate data efficiency of modeling human feedback that is in natural language. Specifically, we fine-tune an open-source LLM, e.g., Falcon-40B-Instruct, on a relatively small amount (1000 records or even less) of human feedback in natural language in the form of critiques and revisions of responses. We show that this model is able to improve the quality of responses from even some of the strongest LLMs such as ChatGPT, BARD, and Vicuna, through critique and revision of those responses. For instance, through one iteration of revision of ChatGPT responses, the revised responses have 56.6% win rate over the original ones, and this win rate can be further improved to 65.9% after applying the revision for five iterations.

A Survey on Fairness-aware Recommender Systems

As information filtering services, recommender systems have extremely enriched our daily life by providing personalized suggestions and facilitating people in decision-making, which makes them vital and indispensable to human society in the information era. However, as people become more dependent on them, recent studies show that recommender systems potentially own unintentional impacts on society and individuals because of their unfairness (e.g., gender discrimination in job recommendations). To develop trustworthy services, it is crucial to devise fairness-aware recommender systems that can mitigate these bias issues. In this survey, we summarise existing methodologies and practices of fairness in recommender systems. Firstly, we present concepts of fairness in different recommendation scenarios, comprehensively categorize current advances, and introduce typical methods to promote fairness in different stages of recommender systems. Next, after introducing datasets and evaluation metrics applied to assess the fairness of recommender systems, we will delve into the significant influence that fairness-aware recommender systems exert on real-world industrial applications. Subsequently, we highlight the connection between fairness and other principles of trustworthy recommender systems, aiming to consider trustworthiness principles holistically while advocating for fairness. Finally, we summarize this review, spotlighting promising opportunities in comprehending concepts, frameworks, the balance between accuracy and fairness, and the ties with trustworthiness, with the ultimate goal of fostering the development of fairness-aware recommender systems.