LongSafetyBench: Long-Context LLMs Struggle with Safety Issues

With the development of large language models (LLMs), the sequence length of these models continues to increase, drawing significant attention to long-context language models. However, the evaluation of these models has been primarily limited to their capabilities, with a lack of research focusing on their safety. Existing work, such as ManyShotJailbreak, has to some extent demonstrated that long-context language models can exhibit safety concerns. However, the methods used are limited and lack comprehensiveness. In response, we introduce \textbf{LongSafetyBench}, the first benchmark designed to objectively and comprehensively evaluate the safety of long-context models. LongSafetyBench consists of 10 task categories, with an average length of 41,889 words. After testing eight long-context language models on LongSafetyBench, we found that existing models generally exhibit insufficient safety capabilities. The proportion of safe responses from most mainstream long-context LLMs is below 50\%. Moreover, models' safety performance in long-context scenarios does not always align with that in short-context scenarios. Further investigation revealed that long-context models tend to overlook harmful content within lengthy texts. We also proposed a simple yet effective solution, allowing open-source models to achieve performance comparable to that of top-tier closed-source models. We believe that LongSafetyBench can serve as a valuable benchmark for evaluating the safety capabilities of long-context language models. We hope that our work will encourage the broader community to pay attention to the safety of long-context models and contribute to the development of solutions to improve the safety of long-context LLMs.

MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential. Existing alignment techniques, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), typically embed predefined preferences directly within the model's parameters. These methods, however, often result in a static alignment that can not account for the diversity of human preferences in practical applications. In response to this challenge, we propose an effective method, \textbf{MetaAlign}, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time. Experimental results show that LLMs optimized on our meticulously constructed MetaAlign Dataset can effectively align with any preferences specified at the inference stage, validating the feasibility of MetaAlign. We hope that our work can provide some insights into the alignment of language models.

Calibrating the Confidence of Large Language Models by Eliciting Fidelity

Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless. However, post-alignment, these language models often exhibit overconfidence, where the expressed confidence does not accurately calibrate with their correctness rate. In this paper, we decompose the language model confidence into the \textit{Uncertainty} about the question and the \textit{Fidelity} to the answer generated by language models. Then, we propose a plug-and-play method to estimate the confidence of language models. Our method has shown good calibration performance by conducting experiments with 6 RLHF-LMs on four MCQA datasets. Moreover, we propose two novel metrics, IPR and CE, to evaluate the calibration of the model, and we have conducted a detailed discussion on \textit{Truly Well-Calibrated Confidence}. Our method could serve as a strong baseline, and we hope that this work will provide some insights into the model confidence calibration.

Labeled Interactive Topic Models

Topic models help users understand large document collections; however, topic models do not always find the ``right'' topics. While classical probabilistic and anchor-based topic models have interactive variants to guide models toward better topics, such interactions are not available for neural topic models such as the embedded topic model (\abr{etm}). We correct this lacuna by adding an intuitive interaction to neural topic models: users can label a topic with a word, and topics are updated so that the topic words are close to the label. This allows a user to refine topics based on their information need. While, interactivity is intuitive for \abr{etm}, we extend this framework to work with other neural topic models as well. We develop an interactive interface which allows users to interact and relabel topic models as they see fit. We evaluate our method through a human study, where users can relabel topics to find relevant documents. Using our method, user labeling improves document rank scores, helping to find more relevant documents to a given query when compared to no user labeling.

Evaluating Hallucinations in Chinese Large Language Models

In this paper, we establish a benchmark named HalluQA (Chinese Hallucination Question-Answering) to measure the hallucination phenomenon in Chinese large language models. HalluQA contains 450 meticulously designed adversarial questions, spanning multiple domains, and takes into account Chinese historical culture, customs, and social phenomena. During the construction of HalluQA, we consider two types of hallucinations: imitative falsehoods and factual errors, and we construct adversarial samples based on GLM-130B and ChatGPT. For evaluation, we design an automated evaluation method using GPT-4 to judge whether a model output is hallucinated. We conduct extensive experiments on 24 large language models, including ERNIE-Bot, Baichuan2, ChatGLM, Qwen, SparkDesk and etc. Out of the 24 models, 18 achieved non-hallucination rates lower than 50%. This indicates that HalluQA is highly challenging. We analyze the primary types of hallucinations in different types of models and their causes. Additionally, we discuss which types of hallucinations should be prioritized for different types of models.

PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search

Few-shot Named Entity Recognition (NER) is a task aiming to identify named entities via limited annotated samples. Recently, prototypical networks have shown promising performance in few-shot NER. Most of prototypical networks will utilize the entities from the support set to construct label prototypes and use the query set to compute span-level similarities and optimize these label prototype representations. However, these methods are usually unsuitable for fine-tuning in the target domain, where only the support set is available. In this paper, we propose PromptNER: a novel prompting method for few-shot NER via k nearest neighbor search. We use prompts that contains entity category information to construct label prototypes, which enables our model to fine-tune with only the support set. Our approach achieves excellent transfer learning ability, and extensive experiments on the Few-NERD and CrossNER datasets demonstrate that our model achieves superior performance over state-of-the-art methods.

A Dataset and Baselines for Multilingual Reply Suggestion

Reply suggestion models help users process emails and chats faster. Previous work only studies English reply suggestion. Instead, we present MRS, a multilingual reply suggestion dataset with ten languages. MRS can be used to compare two families of models: 1) retrieval models that select the reply from a fixed set and 2) generation models that produce the reply from scratch. Therefore, MRS complements existing cross-lingual generalization benchmarks that focus on classification and sequence labeling tasks. We build a generation model and a retrieval model as baselines for MRS. The two models have different strengths in the monolingual setting, and they require different strategies to generalize across languages. MRS is publicly available at https://github.com/zhangmozhi/mrs.

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth

Graph Neural Networks (GNNs) have been studied through the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN training by studying the gradient dynamics of GNNs. First, we analyze linearized GNNs and prove that despite the non-convexity of training, convergence to a global minimum at a linear rate is guaranteed under mild assumptions that we validate on real-world graphs. Second, we study what may affect the GNNs' training speed. Our results show that the training of GNNs is implicitly accelerated by skip connections, more depth, and/or a good label distribution. Empirical results confirm that our theoretical results for linearized GNNs align with the training behavior of nonlinear GNNs. Our results provide the first theoretical support for the success of GNNs with skip connections in terms of optimization, and suggest that deep GNNs with skip connections would be promising in practice.

Noisy Labels Can Induce Good Representations

The current success of deep learning depends on large-scale labeled datasets. In practice, high-quality annotations are expensive to collect, but noisy annotations are more affordable. Previous works report mixed empirical results when training with noisy labels: neural networks can easily memorize random labels, but they can also generalize from noisy labels. To explain this puzzle, we study how architecture affects learning with noisy labels. We observe that if an architecture "suits" the task, training with noisy labels can induce useful hidden representations, even when the model generalizes poorly; i.e., the last few layers of the model are more negatively affected by noisy labels. This finding leads to a simple method to improve models trained on noisy labels: replacing the final dense layers with a linear model, whose weights are learned from a small set of clean data. We empirically validate our findings across three architectures (Convolutional Neural Networks, Graph Neural Networks, and Multi-Layer Perceptrons) and two domains (graph algorithmic tasks and image classification). Furthermore, we achieve state-of-the-art results on image classification benchmarks by combining our method with existing approaches on noisy label training.

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural networks: while multilayer perceptrons (MLPs) do not extrapolate well in certain simple tasks, Graph Neural Network (GNN), a structured network with MLP modules, has shown some success in more complex tasks. Working towards a theoretical explanation, we identify conditions under which MLPs and GNNs extrapolate well. First, we quantify the observation that ReLU MLPs quickly converge to linear functions along any direction from the origin, which implies that ReLU MLPs do not extrapolate most non-linear functions. But, they can provably learn a linear target function when the training distribution is sufficiently "diverse". Second, in connection to analyzing successes and limitations of GNNs, these results suggest a hypothesis for which we provide theoretical and empirical evidence: the success of GNNs in extrapolating algorithmic tasks to new data (e.g., larger graphs or edge weights) relies on encoding task-specific non-linearities in the architecture or features.