论文检索

Kun Luo, Zheng Liu, Shitao Xiao, Tong Zhou, Yubo Chen, Jun Zhao, Kang Liu

Retrieval augmentation is a promising approach to handle long-context language modeling. However, the existing retrieval methods usually work with the chunked context, which is prone to inferior quality of semantic representation and incomplete retrieval of useful information. In this work, we propose a new method for the retrieval augmentation of long-context language modeling, called Landmark Embedding. Our method is characterized by threefold technical contributions. Firstly, we introduce a chunking-free architecture, which keeps the long context coherent such that high-quality embeddings can be generated for the fine-grained units within the context. Secondly, we present a position-aware objective function, which prioritizes the ultimate boundary for a consecutive span of information. By learning to discriminate such a special position, the useful information can be comprehensively retrieved for the query. Thirdly, we design a novel multi-stage learning algorithm, which makes the best use of readily available data and synthetic data for cost-effective training of the landmark embedding. In our experimental study, landmark embedding is able to substantially improve the performance for both LLaMA-2 and ChatGPT in a variety of long-context tasks; meanwhile, it also outperforms the existing retrieval methods with a notable advantage. Our model and source code will be made publicly available.

Houxing Ren, Mingjie Zhan, Zhongyuan Wu, Hongsheng Li

In infilling tasks, sub-tokens, representing instances where a complete token is segmented into two parts, often emerge at the boundaries of prefixes, middles, and suffixes. Traditional methods focused on training models at the token level, leading to sub-optimal performance in character-level infilling tasks during the inference stage. Alternately, some approaches considered character-level infilling, but they relied on predicting sub-tokens in inference, yet this strategy diminished ability in character-level infilling tasks due to the large perplexity of the model on sub-tokens. In this paper, we introduce FIM-SE, which stands for Fill-In-the-Middle with both Starting and Ending character constraints. The proposed method addresses character-level infilling tasks by utilizing a line-level format to avoid predicting any sub-token in inference. In addition, we incorporate two special tokens to signify the rest of the incomplete lines, thereby enhancing generation guidance. Extensive experiments demonstrate that our proposed approach surpasses previous methods, offering a significant advantage. Code is available at https://github.com/SenseLLM/FIM-SE.

Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Despite significant strides in multimodal tasks, Multimodal Large Language Models (MLLMs) are plagued by the critical issue of hallucination. The reliable detection of such hallucinations in MLLMs has, therefore, become a vital aspect of model evaluation and the safeguarding of practical application deployment. Prior research in this domain has been constrained by a narrow focus on singular tasks, an inadequate range of hallucination categories addressed, and a lack of detailed granularity. In response to these challenges, our work expands the investigative horizons of hallucination detection. We present a novel meta-evaluation benchmark, MHaluBench, meticulously crafted to facilitate the evaluation of advancements in hallucination detection methods. Additionally, we unveil a novel unified multimodal hallucination detection framework, UNIHD, which leverages a suite of auxiliary tools to validate the occurrence of hallucinations robustly. We demonstrate the effectiveness of UNIHD through meticulous evaluation and comprehensive analysis. We also provide strategic insights on the application of specific tools for addressing various categories of hallucinations.

Chanjun Park, Hyeonwoo Kim, Dahyun Kim, SeongHwan Cho, Sanghoon Kim, Sukyung Lee, Yungi Kim, Hwalsuk Lee

This paper introduces the Open Ko-LLM Leaderboard and the Ko-H5 Benchmark as vital tools for evaluating Large Language Models (LLMs) in Korean. Incorporating private test sets while mirroring the English Open LLM Leaderboard, we establish a robust evaluation framework that has been well integrated in the Korean LLM community. We perform data leakage analysis that shows the benefit of private test sets along with a correlation study within the Ko-H5 benchmark and temporal analyses of the Ko-H5 score. Moreover, we present empirical support for the need to expand beyond set benchmarks. We hope the Open Ko-LLM Leaderboard sets precedent for expanding LLM evaluation to foster more linguistic diversity.

Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang

Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional treatments on them; that is, the alignment problem. To make LLMs better follow user instructions, existing alignment methods primarily focus on further training them. However, the extra training of LLMs is usually expensive in terms of GPU computing; even worse, some LLMs are not accessible for user-demanded training, such as GPTs. In this work, we take a different perspective—Black-Box Prompt Optimization (BPO)—to perform alignments. The idea is to optimize user prompts to suit LLMs’ input understanding, so as to best realize users’ intents without updating LLMs’ parameters. BPO leverages human preferences to optimize prompts, thus making it superior to LLM (e.g., ChatGPT) as a prompt engineer. Moreover, BPO is model-agnostic, and the empirical results demonstrate that the BPO-aligned ChatGPT yields a 22% increase in the win rate against its original version and 10% for GPT-4. Notably, the BPO-aligned LLMs can outperform the same models aligned by PPO and DPO, and it also brings additional performance gains when combining BPO with PPO or DPO. Code and datasets are released at https://github.com/thu-coai/BPO.

Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, Yongping Xiong

Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP, the current methods are severely limited in representing the text-only and image-only data. In this work, we present a new embedding model VISTA for universal multi-modal retrieval. Our work brings forth threefold technical contributions. Firstly, we introduce a flexible architecture which extends a powerful text encoder with the image understanding capability by introducing visual token embeddings. Secondly, we develop two data generation strategies, which bring high-quality composed image-text to facilitate the training of the embedding model. Thirdly, we introduce a multi-stage training algorithm, which first aligns the visual token embedding with the text encoder using massive weakly labeled data, and then develops multi-modal representation capability using the generated composed image-text data. In our experiments, VISTA achieves superior performances across a variety of multi-modal retrieval tasks in both zero-shot and supervised settings. Our model, data, and source code are available at https://github.com/FlagOpen/FlagEmbedding.

Trinh Pham, Khoi Le, Anh Tuan Luu

In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the optimal vocabulary size, ensuring a balance between model complexity and linguistic coverage. Our experiments across multilingual datasets show that our approach greatly improves the F1-Score in several languages. UniBridge is a robust and adaptable solution for cross-lingual systems in various languages, highlighting the significance of initializing embeddings and choosing the right vocabulary size in cross-lingual environments.

Yuyan Chen, Chenwei Wu, Songzhou Yan, Panjun Liu, Yanghua Xiao

Teachers are important to imparting knowledge and guiding learners, and the role of large language models (LLMs) as potential educators is emerging as an important area of study. Recognizing LLMs’ capability to generate educational content can lead to advances in automated and personalized learning. While LLMs have been tested for their comprehension and problem-solving skills, their capability in teaching remains largely unexplored.In teaching, questioning is a key skill that guides students to analyze, evaluate, and synthesize core concepts and principles.Therefore, our research introduces a benchmark to evaluate the questioning capability in education as a teacher of LLMs through evaluating their generated educational questions, utilizing Anderson and Krathwohl’s taxonomy across general, monodisciplinary, and interdisciplinary domains. We shift the focus from LLMs as learners to LLMs as educators, assessing their teaching capability through guiding them to generate questions. We apply four metrics, including relevance, coverage, representativeness, and consistency, to evaluate the educational quality of LLMs’ outputs. Our results indicate that GPT-4 demonstrates significant potential in teaching general, humanities, and science courses; Claude2 appears more apt as an interdisciplinary teacher. Furthermore, the automatic scores align with human perspectives.

Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou 等

Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases. Recent works have proposed methods to improve LLMs’ long context capabilities by extending context windows and more sophisticated memory mechanisms. However, comprehensive benchmarks tailored for evaluating long context understanding are lacking. In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding. LongBench comprises 21 datasets across 6 task categories in both English and Chinese, with an average length of 6,711 words (English) and 13,386 characters (Chinese). These tasks cover key long-text application areas including single-doc QA, multi-doc QA, summarization, few-shot learning, synthetic tasks, and code completion. All datasets in LongBench are standardized into a unified format, allowing for effortless automatic evaluation of LLMs. Upon comprehensive evaluation of 8 LLMs on LongBench, we find that: (1) Commercial model (GPT-3.5-Turbo-16k) outperforms other open-sourced models, but still struggles on longer contexts. (2) Scaled position embedding and fine-tuning on longer sequences lead to substantial improvement on long context understanding. (3) Context compression technique such as retrieval brings improvement for model with weak ability on long contexts, but the performance still lags behind models that have strong long context understanding capability.

Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen

This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive metrics for systematic evaluation. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to efficiently detoxify LLMs with limited impact on general performance. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxicity of LLMs within a few tuning steps via only one instance. We further provide an in-depth analysis of the internal mechanism for various detoxifying approaches, demonstrating that previous methods like SFT and DPO may merely suppress the activations of toxic parameters, while DINM mitigates the toxicity of the toxic parameters to a certain extent, making permanent adjustments. We hope that these insights could shed light on future work of developing detoxifying approaches and the underlying knowledge mechanisms of LLMs.

Zhou Yang, Zhaochun Ren, Wang Yufeng, Haizhou Sun, Chao Chen, Xiaofei Zhu, Xiangwen Liao

Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates iteratively capturing and understanding associated words across dialogue utterances. However, existing approaches regard dialogue utterances as either a long sequence or independent utterances for comprehension, which are prone to overlook the associated words between them. To address this issue, we propose an Iterative Associative Memory Model (IAMM) for empathetic response generation. Specifically, we employ a novel second-order interaction attention mechanism to iteratively capture vital associated words between dialogue utterances and situations, dialogue history, and a memory module (for storing associated words), thereby accurately and nuancedly comprehending the utterances.We conduct experiments on the Empathetic-Dialogue dataset. Both automatic and human evaluations validate the efficacy of the model. Variant experiments on LLMs also demonstrate that attending to associated words improves empathetic comprehension and expression.

Yongqi Tong, Dawei Li, Sizhe Wang, Yujia Wang, Fei Teng, Jingbo Shang

Large language models (LLMs) have demonstrated striking reasoning capability. Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While humans can indeed imitate correct examples, learning from our mistakes is another vital aspect of human cognition. Hence, a question naturally arises: can LLMs learn and benefit from their mistakes, especially for their reasoning?This study investigates this problem from both the prompting and model-tuning perspectives. We begin by introducing CoTErrorSet, a new benchmark with 609,432 questions, each designed with both correct and error references, and demonstrating the types and reasons for making such mistakes. To explore the effectiveness of those mistakes, we design two methods: (1) Self-rethinking prompting guides LLMs to rethink whether they have made similar previous mistakes; and (2) Mistake tuning involves finetuning models in both correct and incorrect reasoning domains, rather than only tuning models to learn ground truth in traditional methodology. We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions. Our two methods offer potentially cost-effective strategies by leveraging errors to enhance reasoning capabilities, which costs significantly less than creating meticulously hand-crafted golden references. We ultimately make a thorough analysis of the reasons behind LLMs’ errors, which provides directions that future research needs to overcome. CoTErrorSet will be published soon on https://github.com/YookiTong/Learn-from-Mistakes-CotErrorSet.

Pengjie Ren, Chengshun Shi, Shiguang Wu, Mengqi Zhang, Zhaochun Ren, Maarten de Rijke, Zhumin Chen, Jiahuan Pei

Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models’ scale and the diversity of tasks increase. Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional, i.e., significant model changes can be represented with relatively few parameters. However, decreasing the rank encounters challenges with generalization errors for specific tasks when compared to full-parameter fine-tuning. We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank, thereby offering improved performance potential.The core idea is to freeze original pretrained weights and train a group of mini LoRAs with only a small number of parameters. This can capture a significant degree of diversity among mini LoRAs, thus promoting better generalization ability. We conduct a theoretical analysis and empirical studies on various NLP tasks. Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks, which demonstrates the effectiveness of MELoRA.

Zeyu Gao, Hao Wang, Yuanda Wang, Chao Zhang

Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs.Despite its significance, this critical task is impeded by the complexities involved in building high-quality datasets. This paper explores training a Large Language Model (LLM) to emulate a general compiler. By leveraging Ubuntu packages to compile a dataset of 20 billion tokens, we further continue pre-train CodeLlama as a Virtual Compiler (ViC), capable of compiling any source code to assembly code. This approach allows for “virtual” compilation across a wide range of programming languages without the need for a real compiler, preserving semantic equivalency and expanding the possibilities for assembly code dataset construction. Furthermore, we use ViC to construct a sufficiently large dataset for assembly code search. Employing this extensive dataset, we achieve a substantial improvement in assembly code search performance, with our model surpassing the leading baseline by 26%.

Santosh T.Y.S.S, Tuan-Quang Vuong, Matthias Grabmair

This study investigates the challenges posed by the dynamic nature of legal multi-label text classification tasks, where legal concepts evolve over time. Existing models often overlook the temporal dimension in their training process, leading to suboptimal performance of those models over time, as they treat training data as a single homogeneous block. To address this, we introduce ChronosLex, an incremental training paradigm that trains models on chronological splits, preserving the temporal order of the data. However, this incremental approach raises concerns about overfitting to recent data, prompting an assessment of mitigation strategies using continual learning and temporal invariant methods. Our experimental results over six legal multi-label text classification datasets reveal that continual learning methods prove effective in preventing overfitting thereby enhancing temporal generalizability, while temporal invariant methods struggle to capture these dynamics of temporal shifts.

Shuofei Qiao, Ningyu Zhang, Runnan Fang, Yujie Luo, Wangchunshu Zhou, Yuchen Jiang, Chengfei Lv, Huajun Chen

Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework for QA that does not rely on large-scale annotated data and synthetic planning trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. Further analysis demonstrates the effectiveness of the division-of-labor strategy, with the trajectory quality generated by AutoAct generally outperforming that of others.

Qingkai Min, Qipeng Guo, Xiangkun Hu, Songfang Huang, Zheng Zhang, Yue Zhang

Cross-document event coreference resolution (CDECR) involves clustering event mentions across multiple documents that refer to the same real-world events. Existing approaches utilize fine-tuning of small language models (SLMs) like BERT to address the compatibility among the contexts of event mentions. However, due to the complexity and diversity of contexts, these models are prone to learning simple co-occurrences. Recently, large language models (LLMs) like ChatGPT have demonstrated impressive contextual understanding, yet they encounter challenges in adapting to specific information extraction (IE) tasks. In this paper, we propose a collaborative approach for CDECR, leveraging the capabilities of both a universally capable LLM and a task-specific SLM. The collaborative strategy begins with the LLM accurately and comprehensively summarizing events through prompting. Then, the SLM refines its learning of event representations based on these insights during fine-tuning. Experimental results demonstrate that our approach surpasses the performance of both the large and small language models individually, forming a complementary advantage. Across various datasets, our approach achieves state-of-the-art performance, underscoring its effectiveness in diverse scenarios.

Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong, Wei Bi

Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathematical knowledge or merely rely on shortcuts for mathematical reasoning. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs’ math reasoning capability by testing a wide range of question variations. We introduce the adversarial grade school math (GSM-Plus) dataset, an extension of GSM8K augmented with various mathematical perturbations. Our experiments on 25 LLMs and 4 prompting techniques show that while LLMs exhibit different levels of math reasoning abilities, their performances are far from robust. In particular, even for problems that have been solved in GSM8K, LLMs can make mistakes when new statements are added or the question targets are altered. We also explore whether more robust performance can be achieved by composing existing prompting methods, in which we try an iterative method that generates and verifies each intermediate thought based on its reasoning goal and calculation result.

Qiwei Li, Zuchao Li, Ping Wang, Haojun Ai, Hai Zhao

Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relationship between text nodes and the relation between text content. The existing document understanding models mainly focus on entity categories while ignoring the extraction of entity boundaries. We build a novel hypergraph attention document semantic entity recognition framework, HGA, which uses hypergraph attention to focus on entity boundaries and entity categories at the same time. It can conduct a more detailed analysis of the document text representation analyzed by the upstream model and achieves a better performance of semantic information. We apply this method on the basis of GraphLayoutLM to construct a new semantic entity recognition model HGALayoutLM. Our experiment results on FUNSD, CORD, XFUND and SROIE show that our method can effectively improve the performance of semantic entity recognition tasks based on the original model. The results of HGALayoutLM on FUNSD and XFUND reach the new state-of-the-art results.

Chengyu Huang, Zeqiu Wu, Yushi Hu, Wenya Wang

While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to these issues would be to include in-text citations referring to external documents as evidence. While previous works have directly prompted LLMs to generate in-text citations, their performances are far from satisfactory, especially when it comes to smaller LLMs. In this work, we propose an effective training framework using fine-grained rewards to teach LLMs to generate highly supportive and relevant citations, while ensuring the correctness of their responses. We also conduct a systematic analysis of applying these fine-grained rewards to common LLM training strategies, demonstrating its advantage over conventional practices. We conduct extensive experiments on Question Answering (QA) datasets taken from the ALCE benchmark and validate the model’s generalizability using EXPERTQA. On LLaMA-2-7B, the incorporation of fine-grained rewards achieves the best performance among the baselines, even surpassing that of GPT-3.5-turbo.