Large-scale multilingual Pretrained Language Models (mPLMs) yield impressive performance on cross-language tasks, yet significant performance disparities exist across different languages within the same mPLM. Previous studies endeavored to narrow these disparities by supervise fine-tuning the mPLMs with multilingual data. However, obtaining labeled multilingual data is time-consuming, and fine-tuning mPLM with limited labeled multilingual data merely encapsulates the knowledge specific to the labeled data. Therefore, we introduce ALSACE to leverage the learned knowledge from the well-performing languages to guide under-performing ones within the same mPLM, eliminating the need for additional labeled multilingual data. Experiments show that ALSACE effectively mitigates language-level performance disparity across various mPLMs while showing the competitive performance on different multilingual NLU tasks, ranging from full resource to limited resource settings. The code for our approach is available at https://github.com/pkunlp-icler/ALSACE.

Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types, and prompt them with unseen event definitions. These approaches yield sporadic successes, yet generally fall short of expectations. In this work, we aim to improve zero-shot event detection by training models to better follow event definitions. We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while existing event extraction datasets focus on annotating many high-quality examples for a few event types. To verify our hypothesis, we construct an automatically generated Diverse Event Definition (DivED) dataset and conduct comparative studies. Our experiments reveal that a large number of event types (200) and diverse event definitions can significantly boost event extraction performance; on the other hand, the performance does not scale with over ten examples per event type. Beyond scaling, we incorporate event ontology information and hard-negative samples during training, further boosting the performance. Based on these findings, we fine-tuned a LLaMA-2-7B model on our DivED dataset, yielding performance that surpasses SOTA large language models like GPT-3.5 across three open benchmarks on zero-shot event detection.

In this study, we explore the potential of Multimodal Large Language Models (MLLMs) in improving embodied decision-making processes for agents. While Large Language Models (LLMs) have been widely used due to their advanced reasoning skills and vast world knowledge, MLLMs like GPT4-Vision offer enhanced visual understanding and reasoning capabilities. We investigate whether state-of-the-art MLLMs can handle embodied decision-making in an end-to-end manner and whether collaborations between LLMs and MLLMs can enhance decision-making. To address these questions, we introduce a new benchmark called PCA-EVAL, which evaluates embodied decision-making from the perspectives of Perception, Cognition, and Action. Additionally, we propose HOLMES, a multi-agent cooperation framework that allows LLMs to leverage MLLMs and APIs to gather multimodal information for informed decision-making. We compare end-to-end embodied decision-making and HOLMES on our benchmark and find that the GPT4-Vision model demonstrates strong end-to-end embodied decision-making abilities, outperforming GPT4-HOLMES in terms of average decision accuracy (+3%). However, this performance is exclusive to the latest GPT4-Vision model, surpassing the open-source state-of-the-art MLLM by 26%. Our results indicate that powerful MLLMs like GPT4-Vision hold promise for decision-making in embodied agents, offering new avenues for MLLM research. The capacity to make well-informed decisions is essential for the survival and success of living organisms in their respective environments. Similarly, a major goal in embodied artificial intelligence is to develop agents, like robots, with sophisticated decision-making abilities. Recently, there has been a notable increase in leveraging exceptional reasoning capabilities and world knowledge of Large Language Models (LLMs) to enhance decision making in agents. However, LLMs are primarily designed to process textual context, creating a modality gap (Liang et al., 2022; Ren et al., 2023a) for the LLM-powered agent when dealing with multimodal observations in real-world scenarios.

Large language models have shown promising performance in code generation benchmarks. However, a considerable divide exists between these benchmark achievements and their practical applicability, primarily attributed to real-world programming's reliance on pre-existing libraries. Instead of evaluating LLMs to code from scratch, this work aims to propose a new evaluation setup where LLMs use open-source libraries to finish machine learning tasks. Therefore, we propose ML-Bench, an expansive benchmark developed to assess the effectiveness of LLMs in leveraging existing functions in open-source libraries. Consisting of 10044 samples spanning 130 tasks over 14 notable machine learning GitHub repositories. In this setting, given a specific machine learning task instruction and the accompanying README in a codebase, an LLM is tasked to generate code to accomplish the task. This necessitates the comprehension of long and language-code interleaved documents, as well as the understanding of complex cross-file code structures, introducing new challenges. Notably, while GPT-4 exhibits remarkable improvement over other LLMs, it manages to accomplish only 39.73\% of the tasks, leaving a huge space for improvement. We address these challenges by proposing ML-Agent, designed to effectively navigate the codebase, locate documentation, retrieve code, and generate executable code. Empirical results demonstrate that ML-Agent, built upon GPT-4, results in further improvements. Code, data, and models are available at \url{https://ml-bench.github.io/}.

Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing MMICL, a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts. Our experiments confirm that MMICL achieves new state-of-the-art zero-shot performance on a wide range of general vision-language tasks, especially for complex benchmarks, including MME and MMBench. Our analysis demonstrates that MMICL effectively tackles the challenge of complex multi-modal prompt understanding and emerges the impressive ICL ability. Furthermore, we observe that MMICL successfully alleviates language bias in VLMs, a common issue for VLMs that often leads to hallucination when faced with extensive textual context.

In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e.g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models. We find that the quality ranking of candidate responses can be easily hacked by simply altering their order of appearance in the context. This manipulation allows us to skew the evaluation result, making one model appear considerably superior to the other, e.g., Vicuna-13B could beat ChatGPT on 66 over 80 tested queries with ChatGPT as an evaluator. To address this issue, we propose a calibration framework with three simple yet effective strategies: 1) Multiple Evidence Calibration, which requires the evaluator model to generate multiple evaluation evidence before assigning ratings; 2) Balanced Position Calibration, which aggregates results across various orders to determine the final score; 3) Human-in-the-Loop Calibration, which introduces a balanced position diversity entropy to measure the difficulty of each example and seeks human assistance when needed. We also manually annotate the "win/tie/lose" outcomes of responses from ChatGPT and Vicuna-13B in the Vicuna Benchmark's question prompt, and extensive experiments demonstrate that our approach successfully mitigates evaluation bias, resulting in closer alignment with human judgments. We release our code and human annotation at \url{https://github.com/i-Eval/FairEval} to facilitate future research.

Distantly-Supervised Named Entity Recognition effectively alleviates the burden of time-consuming and expensive annotation in the supervised setting. But the context-free matching process and the limited coverage of knowledge bases introduce inaccurate and incomplete annotation noise respectively. Previous studies either considered only incomplete annotation noise or indiscriminately handle two types of noise with the same strategy. In this paper, we argue that the different causes of two types of noise bring up the requirement of different strategies in model architecture. Therefore, we propose the SANTA to handle these two types of noise separately with (1) Memory-smoothed Focal Loss and Entity-aware KNN to relieve the entity ambiguity problem caused by inaccurate annotation, and (2) Boundary Mixup to alleviate decision boundary shifting problem caused by incomplete annotation and a noise-tolerant loss to improve the robustness. Benefiting from our separate tailored strategies, we confirm in the experiment that the two types of noise are well mitigated. SANTA also achieves a new state-of-the-art on five public datasets.

While the emergence of powerful language models along with Chain-of-thought prompting has made automation more and more omnipresent, it sometimes demonstrates its weakness in long-term or multi-step logical reasoning. For example, users don't always get desirable answers for complex mathematical problems without human involvement. Against this background, we present the Manual Correction System (MCS) -- a human-in-the-loop system enhanced by Chain-of-Thought prompting, which explores how manual correction of sub-logics in rationales can improve LLM's reasoning performance. Moving one step forward, considering a system with human-in-the-loop involves more than having humans improve performance but also controlling the cost. Therefore, we post a Cost-utility Analysis Model for Human-in-the-Loop systems (CAMLOP) based on classical economics theory to analyze, quantify and balance the utility and the corresponding cost. We conduct experiments of MCS and CAMLOP with twelve datasets. A significant advantage w.r.t cost and utility proves its superiority over strong baselines.

In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates. Within the newly added data, new intents would emerge and might have semantic entanglement with the existing intents, e.g. new intents that are semantically too specific or generic are actually subset or superset of some existing intents in the semantic space, thus impairing the robustness of the NLU model. As the first attempt to solve this problem, we setup a new benchmark consisting of 4 Dialogue Version Control dataSets (DialogVCS). We formulate the intent detection with imperfect data in the system update as a multi-label classification task with positive but unlabeled intents, which asks the models to recognize all the proper intents, including the ones with semantic entanglement, in the inference. We also propose comprehensive baseline models and conduct in-depth analyses for the benchmark, showing that the semantically entangled intents can be effectively recognized with an automatic workflow.

Current image captioning works usually focus on generating descriptions in an autoregressive manner. However, there are limited works that focus on generating descriptions non-autoregressively, which brings more decoding diversity. Inspired by the success of diffusion models on generating natural-looking images, we propose a novel method DiffCap to apply continuous diffusions on image captioning. Unlike image generation where the output is fixed-size and continuous, image description length varies with discrete tokens. Our method transforms discrete tokens in a natural way and applies continuous diffusion on them to successfully fuse extracted image features for diffusion caption generation. Our experiments on COCO dataset demonstrate that our method uses a much simpler structure to achieve comparable results to the previous non-autoregressive works. Apart from quality, an intriguing property of DiffCap is its high diversity during generation, which is missing from many autoregressive models. We believe our method on fusing multimodal features in diffusion language generation will inspire more researches on multimodal language generation tasks for its simplicity and decoding flexibility.