Language Models Hallucinate, but May Excel at Fact Verification

Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently "hallucinate," resulting in non-factual outputs. Our carefully designed human evaluation substantiates the serious hallucination issue, revealing that even GPT-3.5 produces factual outputs less than 25% of the time. This underscores the importance of fact verifiers in order to measure and incentivize progress. Our systematic investigation affirms that LLMs can be repurposed as effective fact verifiers with strong correlations with human judgments, at least in the Wikipedia domain. Surprisingly, FLAN-T5-11B, the least factual generator in our study, performs the best as a fact verifier, even outperforming more capable LLMs like GPT3.5 and ChatGPT. Delving deeper, we analyze the reliance of these LLMs on high-quality evidence, as well as their deficiencies in robustness and generalization ability. Our study presents insights for developing trustworthy generation models.

Unified Pretraining for Recommendation via Task Hypergraphs

Although pretraining has garnered significant attention and popularity in recent years, its application in graph-based recommender systems is relatively limited. It is challenging to exploit prior knowledge by pretraining in widely used ID-dependent datasets. On one hand, user-item interaction history in one dataset can hardly be transferred to other datasets through pretraining, where IDs are different. On the other hand, pretraining and finetuning on the same dataset leads to a high risk of overfitting. In this paper, we propose a novel multitask pretraining framework named Unified Pretraining for Recommendation via Task Hypergraphs. For a unified learning pattern to handle diverse requirements and nuances of various pretext tasks, we design task hypergraphs to generalize pretext tasks to hyperedge prediction. A novel transitional attention layer is devised to discriminatively learn the relevance between each pretext task and recommendation. Experimental results on three benchmark datasets verify the superiority of UPRTH. Additional detailed investigations are conducted to demonstrate the effectiveness of the proposed framework.

Knowledge Graph Context-Enhanced Diversified Recommendation

The field of Recommender Systems (RecSys) has been extensively studied to enhance accuracy by leveraging users' historical interactions. Nonetheless, this persistent pursuit of accuracy frequently engenders diminished diversity, culminating in the well-recognized "echo chamber" phenomenon. Diversified RecSys has emerged as a countermeasure, placing diversity on par with accuracy and garnering noteworthy attention from academic circles and industry practitioners. This research explores the realm of diversified RecSys within the intricate context of knowledge graphs (KG). These KGs act as repositories of interconnected information concerning entities and items, offering a propitious avenue to amplify recommendation diversity through the incorporation of insightful contextual information. Our contributions include introducing an innovative metric, Entity Coverage, and Relation Coverage, which effectively quantifies diversity within the KG domain. Additionally, we introduce the Diversified Embedding Learning (DEL) module, meticulously designed to formulate user representations that possess an innate awareness of diversity. In tandem with this, we introduce a novel technique named Conditional Alignment and Uniformity (CAU). It adeptly encodes KG item embeddings while preserving contextual integrity. Collectively, our contributions signify a substantial stride towards augmenting the panorama of recommendation diversity within the realm of KG-informed RecSys paradigms.

Multi-omics Sampling-based Graph Transformer for Synthetic Lethality Prediction

Synthetic lethality (SL) prediction is used to identify if the co-mutation of two genes results in cell death. The prevalent strategy is to abstract SL prediction as an edge classification task on gene nodes within SL data and achieve it through graph neural networks (GNNs). However, GNNs suffer from limitations in their message passing mechanisms, including over-smoothing and over-squashing issues. Moreover, harnessing the information of non-SL gene relationships within large-scale multi-omics data to facilitate SL prediction poses a non-trivial challenge. To tackle these issues, we propose a new multi-omics sampling-based graph transformer for SL prediction (MSGT-SL). Concretely, we introduce a shallow multi-view GNN to acquire local structural patterns from both SL and multi-omics data. Further, we input gene features that encode multi-view information into the standard self-attention to capture long-range dependencies. Notably, starting with batch genes from SL data, we adopt parallel random walk sampling across multiple omics gene graphs encompassing them. Such sampling effectively and modestly incorporates genes from omics in a structure-aware manner before using self-attention. We showcase the effectiveness of MSGT-SL on real-world SL tasks, demonstrating the empirical benefits gained from the graph transformer and multi-omics data.

FiLM: Fill-in Language Models for Any-Order Generation

Language models have become the backbone of today's AI systems. However, their predominant left-to-right generation limits the use of bidirectional context, which is essential for tasks that involve filling text in the middle. We propose the Fill-in Language Model (FiLM), a new language modeling approach that allows for flexible generation at any position without adhering to a specific generation order. Its training extends the masked language modeling objective by adopting varying mask probabilities sampled from the Beta distribution to enhance the generative capabilities of FiLM. During inference, FiLM can seamlessly insert missing phrases, sentences, or paragraphs, ensuring that the outputs are fluent and are coherent with the surrounding context. In both automatic and human evaluations, FiLM outperforms existing infilling methods that rely on left-to-right language models trained on rearranged text segments. FiLM is easy to implement and can be either trained from scratch or fine-tuned from a left-to-right language model. Notably, as the model size grows, FiLM's perplexity approaches that of strong left-to-right language models of similar sizes, indicating FiLM's scalability and potential as a large language model.

FedFed: Feature Distillation against Data Heterogeneity in Federated Learning

Federated learning (FL) typically faces data heterogeneity, i.e., distribution shifting among clients. Sharing clients' information has shown great potentiality in mitigating data heterogeneity, yet incurs a dilemma in preserving privacy and promoting model performance. To alleviate the dilemma, we raise a fundamental question: \textit{Is it possible to share partial features in the data to tackle data heterogeneity?} In this work, we give an affirmative answer to this question by proposing a novel approach called {\textbf{Fed}erated \textbf{Fe}ature \textbf{d}istillation} (FedFed). Specifically, FedFed partitions data into performance-sensitive features (i.e., greatly contributing to model performance) and performance-robust features (i.e., limitedly contributing to model performance). The performance-sensitive features are globally shared to mitigate data heterogeneity, while the performance-robust features are kept locally. FedFed enables clients to train models over local and shared data. Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

By reducing the curvature of the loss surface in the parameter space, Sharpness-aware minimization (SAM) yields widespread robustness improvement under domain transfer. Instead of focusing on parameters, however, this work considers the transferability of representations as the optimization target for out-of-domain generalization in a fine-tuning setup. To encourage the retention of transferable representations, we consider trust region-based fine-tuning methods, which exploit task-specific skills without forgetting task-agnostic representations from pre-training. We unify parameter- and representation-space smoothing approaches by using trust region bounds to inform SAM-style regularizers on both of these optimization surfaces. We propose Trust Region Aware Minimization (TRAM), a fine-tuning algorithm that optimizes for flat minima and smooth, informative representations without forgetting pre-trained structure. We find that TRAM outperforms both sharpness-aware and trust region-based optimization methods on cross-domain language modeling and cross-lingual transfer, where robustness to domain transfer and representation generality are critical for success. TRAM establishes a new standard in training generalizable models with minimal additional computation.

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

Large language models (LLMs) are often augmented with tools to solve complex tasks. By generating code snippets and executing them through task-specific Application Programming Interfaces (APIs), they can offload certain functions to dedicated external modules, such as image encoding and performing calculations. However, most existing approaches to augment LLMs with tools are constrained by general-purpose APIs and lack the flexibility for tailoring them to specific tasks. In this work, we present CRAFT, a general tool creation and retrieval framework for LLMs. It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. For each task, we collect specific code solutions by prompting GPT-4 to solve the training examples. Following a validation step ensuring the correctness, these solutions are abstracted into code snippets to enhance reusability, and deduplicated for higher quality. At inference time, the language model retrieves snippets from the toolsets and then executes them or generates the output conditioning on the retrieved snippets. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning. Experiments on vision-language, tabular processing, and mathematical reasoning tasks show that our approach achieves substantial improvements compared to strong baselines. In addition, our in-depth analysis reveals that: (1) consistent performance improvement can be achieved by scaling up the number of tools and the capability of the backbone models; (2) each component of our approach contributes to the performance gains; (3) the created tools are well-structured and reliable with low complexity and atomicity. The code is available at \url{https://github.com/lifan-yuan/CRAFT}.

OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding

Event understanding aims at understanding the content and relationship of events within texts, which covers multiple complicated information extraction tasks: event detection, event argument extraction, and event relation extraction. To facilitate related research and application, we present an event understanding toolkit OmniEvent, which features three desiderata: (1) Comprehensive. OmniEvent supports mainstream modeling paradigms of all the event understanding tasks and the processing of 15 widely-used English and Chinese datasets. (2) Fair. OmniEvent carefully handles the inconspicuous evaluation pitfalls reported in Peng et al. (2023), which ensures fair comparisons between different models. (3) Easy-to-use. OmniEvent is designed to be easily used by users with varying needs. We provide off-the-shelf models that can be directly deployed as web services. The modular framework also enables users to easily implement and evaluate new event understanding models with OmniEvent. The toolkit (https://github.com/THU-KEG/OmniEvent) is publicly released along with the demonstration website and video (https://omnievent.xlore.cn/).

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

To solve complex tasks, large language models (LLMs) often require multiple rounds of interactions with the user, sometimes assisted by external tools. However, current evaluation paradigms often focus solely on benchmark performance with single-turn exchanges, neglecting the intricate interactions among the user, LLMs, and external tools, creating a discrepancy between benchmark evaluation and real-world use cases. We introduce MINT benchmark to evaluate LLMs' ability to solve tasks with multi-turn interactions by (1) using tools and (2) leveraging natural language feedback. To ensure reproducibility, we provide an evaluation framework where LLMs can access tools by executing Python code and receive natural language feedback from the user simulated with GPT-4. We repurpose a diverse set of established datasets and tasks focusing on reasoning, coding, and decision-making and carefully curate them into a compact subset of instances for efficient evaluation. Our analysis of 20 open- and closed-source LLMs offers intriguing findings. (1) LLMs generally benefit from tool interactions and language feedback, with performance gains (absolute, same below) of 1--8% per additional turn with tool use and 2--17% with natural language feedback. (2) Better single-turn performance does not guarantee better multi-turn performance. (3) Surprisingly, on LLMs we evaluated, we found supervised instruction-finetuning (SIFT) and reinforcement learning from human feedback (RLHF) generally hurt multi-turn capabilities. We hope MINT can help measure progress and incentivize research in improving LLMs' capabilities in multi-turn interactions, especially for open-source communities where multi-turn human evaluation has been less accessible compared to commercial LLMs with a larger user base.