论文检索

Ángel Aso-Mollar, Diego Aineto, Enrico Scala, Eva Onaindia

In automated planning, control parameters extend standard action representations through the introduction of continuous numeric decision variables. Existing state-of-the-art approaches have primarily handled control parameters as embedded constraints alongside other temporal and numeric restrictions, and thus have implicitly treated them as additional constraints rather than as decision points in the search space. In this paper, we propose an efficient alternative that explicitly handles control parameters as true decision points within a systematic search scheme. We develop a best-first, heuristic search algorithm that operates over infinite decision spaces defined by control parameters and prove a notion of completeness in the limit under certain conditions. Our algorithm leverages the concept of delayed partial expansion, where a state is not fully expanded but instead incrementally expands a subset of its successors. Our results demonstrate that this novel search algorithm is a competitive alternative to existing approaches for solving planning problems involving control parameters.

Benjamin Aminof, Giuseppe De Giacomo, Sasha Rubin, Moshe Y. Vardi

We study two logics, LTLf+ and PPLTL+, to express properties of infinite traces, that are based on the linear-time temporal logics LTLf and PPLTL on finite traces. LTLf+/PPLTL+ use levels of Manna and Pnueli’s LTL safety-progress hierarchy, and thus have the same expressive power as LTL. However, they also retain a crucial characteristic of reactive synthesis for the base logics: the game arena for strategy extraction can be derived from deterministic finite automata (DFA). Consequently, these logics circumvent the notorious difficulties associated with determinizing infinite trace automata, typical of LTL synthesis. We present optimal DFA-based technique for solving reactive synthesis for LTLf+ and PPLTL+. Additionally, we adapt these algorithms to optimally solve satisfiability and model-checking for these two logics.

Michael Aichmüller, Hector Geffner

In planning and reinforcement learning, the identification of common subgoal structures across problems is important when goals are to be achieved over long horizons. Recently, it has been shown that such structures can be expressed as feature-based rules, called sketches, over a number of classical planning domains. These sketches split problems into subproblems which then become solvable in low polynomial time by a greedy sequence of IW(k) searches. Methods for learning sketches using feature pools and min-SAT solvers have been developed, yet they face two key limitations: scalability and expressivity. In this work, we address these limitations by formulating the problem of learning sketch decompositions as a deep reinforcement learning (DRL) task, where general policies are sought in a modified planning problem where the successor states of a state s are defined as those reachable from s through an IW(k) search. The sketch decompositions obtained through this method are experimentally evaluated across various domains, and problems are regarded as solved by the decomposition when the goal is reached through a greedy sequence of IW(k) searches. While our DRL approach for learning sketch decompositions does not yield interpretable sketches in the form of rules, we demonstrate that the resulting decompositions can often be understood in a crisp manner.

Abdallah Abuaisha, Bojie Shen, Daniel D. Harabor, Peter J. Stuckey, Mark Wallace

Delays in public transport are common, often impacting users through prolonged travel times and missed transfers. Existing solutions for handling delays remain limited; backup plans based on historical data miss opportunities for earlier arrivals, while snapshot planning accounts for current delays but not future ones. With the growing availability of live delay data, users can adjust their journeys in real-time. However, the literature lacks a framework that fully exploits this advantage for system-scale dynamic replanning. To address this, we formalise the dynamic replanning problem in public transport routing and propose two solutions: a "pull" approach, where users manually request replanning, and a novel "push" approach, where the server proactively monitors and adjusts journeys. Our experiments show that the push approach outperforms the pull approach, achieving significant speedups. The results also reveal substantial arrival time savings enabled by dynamic replanning.

Zhengzhong Zhu, Pei Zhou, Zeting Li, Kejiang Chen, Jiangping Zhu

Multi-label text classification (MLTC) is a challenging task where each document can be associated with multiple interdependent labels. This task is complicated by two key issues: the intricate correlations among labels and the partial overlap between labels and text relevance. Existing methods often fail to capture the semantic dependencies between labels or struggle to handle the ambiguities caused by partial overlaps, resulting in suboptimal representation learning. To address these challenges, we propose the Unified Contextual and Label-Aware Framework (UCLAF), which integrates a Label Attention Aware Network(LAN) and Correlation Aware Contrastive Learning (CACL) in a synergistic design. The Label Attention Aware Network explicitly models label dependencies by embedding labels and texts into a shared semantic space, aligning text representations with label semantics. Meanwhile, Correlation Aware Contrastive Learning refines these representations by dynamically modeling sample-level relationships, leveraging a contrastive loss function that accounts for the proportional overlap of labels between samples. This complementary approach enables UCLAF to jointly address complex label correlations and partial label overlaps. Extensive experiments on benchmark datasets demonstrate that UCLAF significantly outperforms state-of-the-art methods, showcasing its effectiveness in improving both representation learning and classification performance in MLTC tasks. We will release our code after the paper is accepted.

Yangfu Zhu, Meiling Li, Yuting Wei, Di Liu, Yuqing Li, Bin Wu

Personality detection aims to identify the personality traits implied in social posts. Existing methods mainly focus on learning the mapping between user-generated posts and personality trait labels but inevitably suffer from potential harm caused by individual bias, as these posts are written by authors from different backgrounds. Learning such spurious associations between posts and traits may lead to the formation of stereotypes, ultimately restricting the detection of personality in different kind of individual. To tackle the issue, we first investigate individual bias in personality detection from the causality perspective. We propose an Interventional Personality Detection Network (IPDN) to learn implicit confounders in user-generated posts and exploit the true causal effect to train the detection model. Specifically, our IPDN disentangled the causal and biased features behind user-generated posts, and then the biased features are accumulatively clustered as confounder prototypes as the training iterations increase. In parallel, the reconstruction network is reused to approximate backdoor adjustment on raw posts, ensuring that traits see each confounder equally before detection. Extensive experiments conducted on three real-world datasets demonstrate that our IPDN outperforms state-of-the-art methods in personality detection.

Wenhao Zhu, Yuhang Xie, Guojie Song, Xin Zhang

The rapid evolution of large language models (LLMs) has revolutionized various fields, including the identification and discovery of human values within text data. While traditional NLP models, such as BERT, have been employed for this task, their ability to represent textual data is significantly outperformed by emerging LLMs like GPTs. However, the performance of online LLMs often degrades when handling long contexts required for value identification, which also incurs substantial computational costs. To address these challenges, we propose EAVIT, an efficient and accurate framework for human value identification that combines the strengths of both locally fine-tunable and online black-box LLMs. Our framework employs a value detector—a small, local language model—to generate initial value estimations. These estimations are then used to construct concise input prompts for online LLMs, enabling accurate final value identification. To train the value detector, we introduce explanation-based training and data generation techniques specifically tailored for value identification, alongside sampling strategies to optimize the brevity of LLM input prompts. Our approach effectively reduces the number of input tokens by up to 1/6 compared to directly querying online LLMs, while consistently outperforming traditional NLP methods and other LLM-based strategies.

Linlin Zhu, Heli Sun, Xiaoyong Huang, Qi Zhang, Ruichen Cao, Liang He

Multimodal aspect-based sentiment analysis aims to extract aspects from different data sources and recognize the corresponding sentiments. While current research has broadly focused on syntax relation-driven semantic comprehension, the impact of the importance of different syntactic relations on semantic understanding has not been adequately investigated. To address this issue, we propose a Sentiment-enhanced Multi-hop Connected Graph Attention Network (MCG), aiming to enhance the discriminative capability of model for sentiments and to delve into the syntactic relationships within the text. Firstly, we design a contrastive sentiment-enhanced pre-training task that expands the diversity and complexity of training samples to improve the recognition of multiple sentiments. Secondly, we construct a multi-hop connected syntactic dependency graph to deeply explore the rich syntactic dependencies in the text and to reveal the differences among syntactic relations. Moreover, we develop a multi-hop connected graph attention mechanism that enables the model to focus on the key syntactic relations within the syntactic structure, thereby enhancing the comprehension and predictive capabilities of model in multimodal sentiment analysis. Experimental results on two benchmark datasets demonstrate that our method outperforms state-of-the-art methods. The source code is provided in the supplementary materials.

Yunxiao Zhang, Guanming Xiong, Haochen Li, Wen Zhao

Large Language Models (LLMs) have shown remarkable capabilities as AI agents. However, existing methods for enhancing LLM-agent abilities often lack a focus on data quality, leading to inefficiencies and suboptimal results in both fine-tuning and prompt engineering. To address this issue, we introduce EDGE, a novel approach for identifying informative samples without needing golden answers. We propose the Guideline Effectiveness (GE) metric, which selects challenging samples by measuring the impact of human-provided guidelines in multi-turn interaction tasks. A low GE score indicates that the human expertise required for a sample is missing from the guideline, making the sample more informative. By selecting samples with low GE scores, we can improve the efficiency and outcomes of both prompt engineering and fine-tuning processes for LLMs. Extensive experiments validate the performance of our method. Our method achieves competitive results on the HotpotQA and WebShop and datasets, requiring 75% and 50% less data, respectively, while outperforming existing methods. We also provide a fresh perspective on the data quality of LLM-agent fine-tuning.

Yang Zhang, Yu Yu, Bo Tang, Yu Zhu, Chuxiong Sun, Wenqiang Wei, Jie Hu, Zipeng Xie, Zhiyu Li, Feiyu Xiong 等

With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However, existing alignment techniques such as RLHF or DPO often require direct fine-tuning on LLMs with billions of parameters, resulting in substantial computational costs and inefficiencies. To address this, we propose Micro token-level Accept-Reject Aligning (MARA) approach designed to operate independently of the language models. MARA simplifies the alignment process by decomposing sentence-level preference learning into token-level binary classification, where a compact three-layer fully-connected network determines whether candidate tokens are “Accepted” or “Rejected” as part of the response. Extensive experiments across seven different LLMs and three open-source datasets show that MARA achieves significant improvements in alignment performance while reducing computational costs. The source code and implementation details are publicly available at https://github.com/IAAR-Shanghai/MARA, and the trained models are released at https://huggingface.co/IAAR-Shanghai/MARA_AGENTS.

Miao Zhang, Jiawei Wang, Jinying Han, Kui Xiao, Zhifei Li, Yan Zhang, Hao Chen, Shihui Wang

Concept prerequisite relations determine the learning order of knowledge concepts in one domain, which has an important impact on teachers' course design and students' personalized learning. Current research usually predicts concept prerequisite relations from the perspective of knowledge, and rarely pays attention to the role of learners' learning behavior. We propose a Dual Graph Distillation Method for Concept Prerequisite Relation Learning (DGCPL). Specifically, DGCPL constructs a dual graph structure from both the knowledge and learning behavior perspectives, and captures the high-order knowledge features and learning behavior features through the concept-resource hypergraph and the learning behavior graph respectively. In addition, we introduce a gated knowledge distillation to fuse the structural information of concept nodes in the two graphs, so as to obtain a more comprehensive concept embedding representation and achieve accurate prediction of prerequisite relations. On three public benchmark datasets, we compare DGCPL with eight graph-based baseline methods and five traditional classification baseline methods. The experimental results show that DGCPL achieves state-of-the-art performance in learning concept prerequisite relations. Our code is available at https://github.com/wisejw/DGCPL.

Luan Zhang, Dandan Song, Zhijing Wu, Yuhang Tian, Changzhi Zhou, Jing Xu, Ziyi Yang, Shuhao Zhang

Large language models (LLMs) have shown exceptional performance across various domains. However, LLMs are prone to hallucinate facts and generate non-factual responses, which can undermine their reliability in real-world applications. Current hallucination detection methods suffer from external resource demands, substantial time overhead, difficulty overcoming LLMs' intrinsic limitation, and insufficient modeling. In this paper, we propose MHAD, a novel internal-representation-based hallucination detection method. MHAD utilizes linear probing to select neurons and layers within LLMs. The selected neurons and layers are demonstrated with significant awareness of hallucinations at the initial and final generation steps. By concatenating the outputs from these selected neurons of selected layers at the initial and final generation steps, a hallucination awareness vector is formed, enabling precise hallucination detection via an MLP. Additionally, we introduce SOQHD, a novel benchmark for evaluating hallucination detection in Open-Domain QA (ODQA). Extensive experiments show that MHAD outperforms existing hallucination detection methods across multiple LLMs, demonstrating superior effectiveness.

Jia Zhang, Chen-Xi Zhang, Yao Liu, Yi-Xuan Jin, Xiao-Wen Yang, Bo Zheng, Yi Liu, Lan-Zhe Guo

Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabilities, outperforming large datasets often burdened by quality and redundancy issues. However, the challenge lies in automatically identifying valuable subsets from large datasets to boost both the effectiveness and efficiency of instruction tuning. In this paper, we first establish data selection criteria based on three distinct aspects of data value: diversity, difficulty, and dependability, and then propose the D3 method comprising two key steps of scoring and selection. Specifically, in the scoring step, we define the diversity function to measure sample distinctiveness and introduce the uncertainty-based prediction difficulty to evaluate sample difficulty by mitigating the interference of context-oriented generation diversity. Additionally, we integrate an external LLM for dependability assessment. In the selection step, we formulate the D3 weighted coreset objective, which jointly optimizes three aspects of data value to solve for the most valuable subset. The two steps of D3 can iterate multiple rounds, incorporating feedback to refine the selection focus adaptively. Experiments on both public datasets and the real-world Taobao Live application demonstrate the effectiveness of D3 in endowing LLMs with competitive or even superior instruction-following capabilities using less than 10% of the entire dataset.

Xinyu Yao, Mengdi Wang, Bo Chen, Xiaobing Zhao

Classical Chinese, as the core carrier of Chinese culture, plays a crucial role in the inheritance and study of ancient literature. However, existing natural language processing models primarily optimize for Modern Chinese, resulting in inadequate performance on Classical Chinese. This paper presents a comprehensive solution for Classical Chinese language processing. By continuing pre-training and instruction fine-tuning on the LLaMA3-8B-Chinese model, we construct a large language model, WenyanGPT, which is specifically designed for Classical Chinese tasks. Additionally, we develop an evaluation benchmark dataset, WenyanBENCH. Experimental results on WenyanBENCH demonstrate that WenyanGPT significantly outperforms current advanced LLMs in various Classical Chinese tasks. We make the model's training data, instruction fine-tuning data, and evaluation benchmark dataset publicly available to promote further research and development in the field of Classical Chinese processing.

Qing Yang, Qiyao Peng, Hongtao Liu, Kai Liu, Bing Qin, Ting Liu

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, with pre-training stage serving as the cornerstone of their capabilities. However, the conventional fixed-length data composition strategy for pre-training presents several practical challenges. When using shorter sequences, documents are often truncated, potentially leading to information loss and affecting the model's ability to capture long-range dependencies. Conversely, longer sequences require concatenation of multiple documents, which can introduce noise and affect the natural document boundaries and semantic coherence as well as require substantial computational overhead. To address these challenges, we first establish three quantitative metrics for evaluating data composition quality: padding ratio, truncation ratio, and concatenation ratio. Building upon these metrics, we propose a novel multi-bucket data composition method that transcends the fixed-length paradigm. Our approach adaptively organizes training data to achieve optimal composition quality as measured by the proposed metrics, offering a more flexible and efficient approach for pre-training. We conduct extensive experiments and the results demonstrate that our proposed method significantly enhances both the efficiency and effectiveness of LLM pre-training. Our proposed method has been adopted in the Du Xiaoman–XuanYuan series of financial large language models at https://github.com/Duxiaoman-DI/XuanYuan.

Xin Xu, Shizhe Diao, Can Yang, Yang Wang

Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing end-task performance. In addition, there has been research on assessing the quality of reasoning chains in CoT. This raises an intriguing question: Is it possible to predict the accuracy of LLM outputs by scrutinizing the reasoning chains they generate? To answer this research question, we introduce a benchmark, R2PE, designed specifically to explore the relationship between reasoning chains and performance in various reasoning tasks spanning five different domains. This benchmark aims to measure the falsehood of the final output of LLMs based on the reasoning steps. To make full use of information in multiple reasoning chains, we propose the process discernibility score (PDS) framework that beats the answer-checking baseline by a large margin. Concretely, this resulted in an average of 5.1% increase in the F1 score and 2.97% improvement in AUC-PR across all 45 subsets within R2PE. We further demonstrate our PDS’s efficacy in advancing open-domain QA accuracy. Our code will be released in the final version. Codes and data are available at https://github.com/XinXU-USTC/R2PE.git. For further details on the appendix, please refer to https://arxiv.org/abs/2402.10528.

Huangming Xu, Fu Zhang, Jingwei Cheng, Xin Li

The goal of document-level relation extraction (DocRE) is to identify relations between entities from multiple sentences. As a multi-label classification task, a common approach is to determine whether there are relations for an entity pair by selecting a multi-label classification threshold, with scores of relations above the threshold predicted as positive and the rest as negative. However, we find that predicting multiple relations for entity pairs causes the decrease of predicted scores in positive classes. This could lead to many positive classes being incorrectly predicted as negative. Additionally, our analysis suggests that fitting the distribution of predicted relations to the prior distribution of relations can help improve prediction performance. However, previous studies have not explored or leveraged the prior distribution of relations. To address these issues and findings, we for the first time propose the idea of incorporating the relational prior distribution into the loss calculation in DocRE tasks. We innovatively propose an Adaptive Relational Prior Distribution Loss (ARPDL), which can adaptively adjust relation prediction scores based on the relational prior distribution. Our designed relational prior distribution component can also be integrated as an adapter into other threshold-based losses to improve prediction performance. Experimental results demonstrate that ARPDL consistently improves the performance of existing DocRE models, achieving new state-of-the-art results. Furthermore, integrating our relational prior distribution adapter into other losses significantly enhances their performance in DocRE tasks, validating the effectiveness and generality of our approach. Code is available at https://github.com/xhm-code/ARPDL.

Bo Xu, Liangzhi Li, Junlong Wang, Xuening Qiao, Erchen Yu, Yiming Qian, Linlin Zong, Hongfei Lin

The rapid development of large language models has greatly advanced human-computer dialogue research. However, applying these models to specialized fields like maternity and infant care often leads to subpar performance due to a lack of domain-specific datasets. To address this problem, we have created MicDialogue, a Chinese dialogue dataset for maternity and infant care. MicDialogue involves a wide range of specialized topics, including gynecological health, pediatric care, pregnancy preparation, emotional counseling and other related topics. This dataset is curated from two types of Chinese social media: short videos and blog posts. Short videos capture real-time interactions and pragmatic dialogue patterns, while blog posts offer comprehensive coverage of various topics within the domain. We have also included detailed annotations for topics, diseases, symptoms, and causes, enabling in-depth research. Additionally, we developed a knowledge-driven benchmark model using LLM-based prompt learning and multiple knowledge graphs to address diverse dialogue topics. Experiments validate MicDialogue's usability, providing benchmarks for future research and essential data for fine-tuning language models in maternity and infant care.

Yifan Wei, Xiaoyan Yu, Ran Song, Hao Peng, Angsheng Li

Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Traditional updating methods, like fine-tuning and incremental learning, face challenges such as overfitting and high computational costs. Knowledge Editing (KE) provides a promising alternative but often overlooks the Knowledge Element Overlap (KEO) phenomenon, where multiple triplets share common elements, leading to editing conflicts. We identify the prevalence of KEO in existing KE datasets and show its significant impact on current KE methods, causing performance degradation in handling such triplets. To address this, we propose a new formulation, Knowledge Set Editing (KSE), and introduce SetKE, a method that edits sets of triplets simultaneously. Experimental results demonstrate that SetKE outperforms existing methods in KEO scenarios on mainstream LLMs. Additionally, we introduce EditSet, a dataset containing KEO triplets, providing a comprehensive benchmark.

Xiao Wei, Xiaobao Wang, Ning Zhuang, Chenyang Wang, Longbiao Wang, Jianwu Dang

Intent detection aims to identify user intents from natural language inputs, where supervised methods rely heavily on labeled in-domain (IND) data and struggle with out-of-domain (OOD) intents, limiting their practical applicability. Generalized Intent Discovery (GID) addresses this by leveraging unlabeled OOD data to discover new intents without additional annotation. However, existing methods focus solely on clustering unsupervised data while neglecting domain adaptation. Therefore, we propose a consistency-driven prototype-prompting framework for GID from the perspective of integrating old and new knowledge, which includes a prototype-prompting framework for transferring old knowledge from external sources, and a hierarchical consistency constraint for learning new knowledge from target domains. We conducted extensive experiments and the results show that our method significantly outperforms all baseline methods, achieving state-of-the-art results, which strongly demonstrates the effectiveness and generalization of our methods. Our source code is publicly available at https://github.com/smileix/cpp.