Legal judgment prediction serves as a pivotal task in intelligent judicial systems.Although Large Language Models (LLMs) have achieved remarkable progress in general reasoning, they struggle with tasks that require fine-grained distinctions between similar charges.These models often select plausible charges directly without discriminating among closely related alternatives.In this paper, we introduce GLARE, an agentic legal reasoning framework that enables models to actively retrieve and apply external knowledge during decision-making.Unlike static prediction, GLARE simulates comparative reasoning by dynamically expanding the decision space to include confusing candidates, then retrieving exclusionary logic from precedents and statutes to identify the correct judgment.Experiments on real-world datasets show that our method significantly outperforms strong baselines, especially on complex cases involving confusing or rare charges.

As a primary means of information acquisition, information retrieval (IR) systems, such as search engines, have integrated themselves into our daily lives. These systems also serve as components of dialogue, question-answering, and recommender systems. The trajectory of IR has evolved dynamically from its origins in term-based methods to its integration with advanced neural models. While the neural models excel at capturing complex contextual signals and semantic nuances, they still face challenges such as data scarcity, interpretability, and the generation of contextually plausible yet potentially inaccurate responses. This evolution requires a combination of traditional methods (such as term-based sparse retrieval methods with rapid response) and modern neural architectures (such as language models with powerful language understanding capacity). Meanwhile, the emergence of large language models (LLMs) has revolutionized natural language processing due to their remarkable language understanding, generation, and reasoning abilities. Consequently, recent research has sought to leverage LLMs to improve IR systems. Given the rapid evolution of this research trajectory, it is necessary to consolidate existing methodologies and provide nuanced insights through a comprehensive overview. In this survey, we delve into the confluence of LLMs and IR systems, including crucial aspects such as query rewriters, retrievers, rerankers, readers, and search agents.

Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Xinting Huang, Dong Yu, Zhicheng Dou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in standard decoder-only Transformers. Although powerful, this method can be inefficient for long sequences and may overlook inherent input structures. To address these problems, an alternative approach is parallel context encoding, which splits the context into sub-pieces and encodes them parallelly. Because parallel patterns are not encountered during training, naively applying parallel encoding leads to performance degradation. However, the underlying reasons and potential mitigations are unclear. In this work, we provide a detailed analysis of this issue and identify that unusually high attention entropy can be a key factor. Furthermore, we adopt two straightforward methods to reduce attention entropy by incorporating attention sinks and selective mechanisms. Experiments on various tasks reveal that these methods effectively lower irregular attention entropy and narrow performance gaps. We hope this study can illuminate ways to enhance context modeling mechanisms.

Accurate vehicular localization systems are essential for enabling the safe execution of cooperative vehicular tasks, though maintaining positioning precision in dynamic and cluttered environments persists as a critical technical challenge. Cooperative positioning leverages inter-vehicle spatial correlations and received data from other nodes in the swarm to enhance localization accuracy and reliability, but still suffers from outlier impacts. To improve system robustness and accuracy in cooperative positioning networks, this paper proposes two cooperative positioning methods based on the centralized mode and the distributed mode respectively, where nodes establish spatial relationships through Ultra-wideband (UWB) inter-node ranging while processing the Global Navigation Satellite System (GNSS) data differently before communication. Semi-simulation experiments quantify two key metrics for comparisons, including positioning accuracy through root mean square error (RMSE), and computational efficiency through the total time cost of processing a period of data. Results demonstrate that proposed cooperative methods achieve a significant reduction on RMSE over the method without cooperation. Comparative analysis also reveals distinct operational characteristics between centralized (CP) and decentralized (DP) positioning architectures: While CP demonstrates marginal accuracy advantages under nominal observation conditions, DP exhibits superior robustness in harsh environments. Notably, DP achieves this performance enhancement with 26.4% reduced computational time compared to CP.

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of KV cache remains a major bottleneck for general-purpose deployment. While many compression strategies have been explored, sequence-level compression is particularly challenging due to its tendency to lose important details. We present UniGist, a gist token-based long context compression framework that removes the need for chunk-wise training, enabling the model to learn how to compress and utilize long-range context during training. To fully exploit the sparsity, we introduce a gist shift trick that transforms the attention layout into a right-aligned block structure and develop a block-table-free sparse attention kernel based on it. UniGist further supports one-pass training and flexible chunk sizes during inference, allowing efficient and adaptive context processing. Experiments across multiple long-context tasks show that UniGist significantly improves compression quality, with especially strong performance in recalling details and long-range dependency modeling.

Legal case retrieval for sourcing similar cases is critical in upholding judicial fairness.Different from general web search, legal case retrieval involves processing lengthy, complex, and highly specialized legal documents.Existing methods in this domain often overlook the incorporation of legal expert knowledge, which is crucial for accurately understanding and modeling legal cases, leading to unsatisfactory retrieval performance.This paper introduces KELLER, a legal knowledge-guided case reformulation approach based on large language models (LLMs) for effective and interpretable legal case retrieval.By incorporating professional legal knowledge about crimes and law articles, we enable large language models to accurately reformulate the original legal case into concise sub-facts of crimes, which contain the essential information of the case.Extensive experiments on two legal case retrieval benchmarks demonstrate superior retrieval performance and robustness on complex legal case queries of KELLER over existing methods.

Conversational search requires accurate interpretation of user intent from complex multiturn contexts.This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent complex conversational sessions for dense retrieval.To achieve this, we propose a simple and effective dual-learning approach that adapts LLM for retrieval via contrastive learning while enhancing the complex session understanding through masked instruction tuning on high-quality conversational instruction tuning data.Extensive experiments on five conversational search benchmarks demonstrate that ChatRetriever substantially outperforms existing conversational dense retrievers, achieving state-of-the-art performance on par with LLM-based rewriting approaches.Furthermore, ChatRetriever exhibits superior robustness in handling diverse conversational contexts.Our work highlights the potential of adapting LLMs for retrieval with complex inputs like conversational search sessions and proposes an effective approach to advance this research direction.

Personalized search improves the quality of search results by modeling historical user behavior. In recent years, many methods based on deep learning have greatly improved the performance of personalized search. However, most of the existing methods only focus on modeling positive user behavior signals, which leads to incomplete user interest modeling. At the same time, the user's search behavior hides much explicit or implicit feedback information. For example, clicking and staying for a certain period represents implicit positive feedback, and skipping behavior represents implicit negative feedback. Intuitively, this information can be utilized to construct a more complete and accurate user profile. In this paper, we propose a dual-feedback modeling framework, which integrates multi-granular user feedback information to model the user's current search intention. Specifically, we propose a feedback extraction network to refine the dual-feedback representation in multiple stages. For enhancing the user's real-time search quality, we design an additional dual-feedback feature gating module to capture the user's real-time feedback in the current session. We conducted a large number of experiments on two real-world datasets, and the experimental results show that our method can effectively improve the performance of personalized search.