Improving Translation Faithfulness of Large Language Models via Augmenting Instructions

Large Language Models (LLMs) present strong general capabilities, and a current compelling challenge is stimulating their specialized capabilities, such as machine translation, through low-cost instruction tuning. The standard instruction-following data is sequentially organized as the concatenation of an instruction, an input, and a response. As the attention mechanism of LLMs has limitations on local focus, LLMs tend to focus more on the words or sentences nearby at each position. This leads to a high risk of instruction forgetting during decoding. To alleviate the above issues, We propose SWIE (Segment-Weighted Instruction Embedding) and an instruction-following dataset OVERMISS. SWIE improves the model instruction understanding by adding a global instruction representation on the following input and response representations. OVERMISS improves model faithfulness by comparing over-translation and miss-translation results with the correct translation. We apply our methods to two main-stream open-source LLMs, BLOOM and LLaMA. The experimental results demonstrate significant improvements in translation performance with SWIE based on BLOOMZ-3b, particularly in zero-shot and long text translations due to reduced instruction forgetting risk. Additionally, OVERMISS outperforms the baseline in translation performance (e.g. an increase in BLEU scores from 0.69 to 3.12 and an average improvement of 0.48 percentage comet scores for LLaMA-7b) with further enhancements seen in models combining OVERMISS and SWIE (e.g. the BLUE scores increase up to 0.56 from English to German across three different backbones), and both exhibit improvements in the faithfulness metric based on word alignment.

Instruction Position Matters in Sequence Generation with Large Language Models

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning data is generally sequentially concatenated from a specific task instruction, an input sentence, and the corresponding response. Considering the locality modeled by the self-attention mechanism of LLMs, these models face the risk of instruction forgetting when generating responses for long input sentences. To mitigate this issue, we propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences. Theoretical analysis suggests that our straightforward method can alter the model's learning focus, thereby emphasizing the training of instruction-following capabilities. Concurrently, experimental results demonstrate that our approach consistently outperforms traditional settings across various model scales (1B / 7B / 13B) and different sequence generation tasks (translation and summarization), without any additional data or annotation costs. Notably, our method significantly improves the zero-shot performance on conditional sequence generation, e.g., up to 9.7 BLEU points on WMT zero-shot translation tasks.

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents

Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework \framework that can collaboratively and dynamically adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that \framework framework can effectively deploy multi-agent groups that outperform a single agent. Furthermore, we delve into the emergence of social behaviors among individual agents within a group during collaborative task accomplishment. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups. Our codes for \framework will soon be released at \url{https://github.com/OpenBMB/AgentVerse}.

An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information as it learns new information. As large language models (LLMs) have shown excellent performance, it is interesting to uncover whether CF exists in the continual fine-tuning of LLMs. In this study, we empirically evaluate the forgetting phenomenon in LLMs' knowledge, from the perspectives of domain knowledge, reasoning, and reading comprehension. The experiments demonstrate that catastrophic forgetting is generally observed in LLMs ranging from 1b to 7b. Furthermore, as the scale increases, the severity of forgetting also intensifies. Comparing the decoder-only model BLOOMZ with the encoder-decoder model mT0, BLOOMZ suffers less forgetting and maintains more knowledge. We also observe that LLMs can mitigate language bias (e.g. gender bias) during continual fine-tuning. Moreover, we find that ALPACA can maintain more knowledge and capacity compared with LLAMA during the continual fine-tuning, which implies that general instruction tuning can help mitigate the forgetting phenomenon of LLMs in the further fine-tuning process.

Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation

N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks. However, recent studies have revealed a weak correlation between these matching-based metrics and human evaluations, especially when compared with neural-based metrics like BLEURT. In this paper, we conjecture that the performance bottleneck in matching-based metrics may be caused by the limited diversity of references. To address this issue, we propose to utilize \textit{multiple references} to enhance the consistency between these metrics and human evaluations. Within the WMT Metrics benchmarks, we observe that the multi-references F200spBLEU surpasses the conventional single-reference one by an accuracy improvement of 7.2\%. Remarkably, it also exceeds the neural-based BERTscore by an accuracy enhancement of 3.9\%. Moreover, we observe that the data leakage issue in large language models (LLMs) can be mitigated to a large extent by our multi-reference metric. We release the code and data at \url{https://github.com/SefaZeng/LLM-Ref}

Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes

3D human pose estimation in outdoor environments has garnered increasing attention recently. However, prevalent 3D human pose datasets pertaining to outdoor scenes lack diversity, as they predominantly utilize only one type of modality (RGB image or pointcloud), and often feature only one individual within each scene. This limited scope of dataset infrastructure considerably hinders the variability of available data. In this article, we propose Human-M3, an outdoor multi-modal multi-view multi-person human pose database which includes not only multi-view RGB videos of outdoor scenes but also corresponding pointclouds. In order to obtain accurate human poses, we propose an algorithm based on multi-modal data input to generate ground truth annotation. This benefits from robust pointcloud detection and tracking, which solves the problem of inaccurate human localization and matching ambiguity that may exist in previous multi-view RGB videos in outdoor multi-person scenes, and generates reliable ground truth annotations. Evaluation of multiple different modalities algorithms has shown that this database is challenging and suitable for future research. Furthermore, we propose a 3D human pose estimation algorithm based on multi-modal data input, which demonstrates the advantages of multi-modal data input for 3D human pose estimation. Code and data will be released on https://github.com/soullessrobot/Human-M3-Dataset.

EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education

EduChat (https://www.educhat.top/) is a large-scale language model (LLM)-based chatbot system in the education domain. Its goal is to support personalized, fair, and compassionate intelligent education, serving teachers, students, and parents. Guided by theories from psychology and education, it further strengthens educational functions such as open question answering, essay assessment, Socratic teaching, and emotional support based on the existing basic LLMs. Particularly, we learn domain-specific knowledge by pre-training on the educational corpus and stimulate various skills with tool use by fine-tuning on designed system prompts and instructions. Currently, EduChat is available online as an open-source project, with its code, data, and model parameters available on platforms (e.g., GitHub https://github.com/icalk-nlp/EduChat, Hugging Face https://huggingface.co/ecnu-icalk ). We also prepare a demonstration of its capabilities online (https://vimeo.com/851004454). This initiative aims to promote research and applications of LLMs for intelligent education.

ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Despite the advancements of open-source large language models (LLMs) and their variants, e.g., LLaMA and Vicuna, they remain significantly limited in performing higher-level tasks, such as following human instructions to use external tools (APIs). This is because current instruction tuning largely focuses on basic language tasks instead of the tool-use domain. This is in contrast to state-of-the-art (SOTA) LLMs, e.g., ChatGPT, which have demonstrated excellent tool-use capabilities but are unfortunately closed source. To facilitate tool-use capabilities within open-source LLMs, we introduce ToolLLM, a general tool-use framework of data construction, model training and evaluation. We first present ToolBench, an instruction-tuning dataset for tool use, which is created automatically using ChatGPT. Specifically, we collect 16,464 real-world RESTful APIs spanning 49 categories from RapidAPI Hub, then prompt ChatGPT to generate diverse human instructions involving these APIs, covering both single-tool and multi-tool scenarios. Finally, we use ChatGPT to search for a valid solution path (chain of API calls) for each instruction. To make the searching process more efficient, we develop a novel depth-first search-based decision tree (DFSDT), enabling LLMs to evaluate multiple reasoning traces and expand the search space. We show that DFSDT significantly enhances the planning and reasoning capabilities of LLMs. For efficient tool-use assessment, we develop an automatic evaluator: ToolEval. We fine-tune LLaMA on ToolBench and obtain ToolLLaMA. Our ToolEval reveals that ToolLLaMA demonstrates a remarkable ability to execute complex instructions and generalize to unseen APIs, and exhibits comparable performance to ChatGPT. To make the pipeline more practical, we devise a neural API retriever to recommend appropriate APIs for each instruction, negating the need for manual API selection.