Mixture-of-Experts (MoE) architectures have recently become a more prevalent choice for large language models (LLMs) than dense architectures due to their superior performance. However, billions of parameters bring MoE LLMs a huge cost for deployment and inference. To address these issues, knowledge distillation (KD) has become a widely adopted technique to compress LLMs. Existing KD methods for LLMs can be divided into dense-to-dense and moe-to-dense distillation. Dense-to-dense distillation transfers knowledge between single dense LLMs, while moe-to-dense distillation attempts to transfer knowledge between the MoE LLMs and the dense LLMs. However, the architectural mismatch prevents the student from fully absorbing knowledge when distilling MoE LLMs. To address this limitation, we investigate a new distillation setting, moe-to-moe, which aims to fully leverage expert knowledge of teachers and enable the student to absorb it more effectively. Compared to dense-to-dense and moe-to-dense, moe-to-moe suffers from two imbalance issues. First, expert-coverage deficiency reflects an imbalanced knowledge transfer of teacher experts: traditional distillation utilizes only the few experts activated by the teacher router. Second, routing imbalance appears when the student routing distribution drifts from the teacher, which makes it difficult for students to learn how to distribute different experts. To overcome these issues, we propose a novel distillation framework for moe-to-moe, Balanced Distillation (B-Distill), which equally spreads teacher expertise across student experts while regularizing the student router toward teacher-consistent balance. First, to mitigate expert-coverage deficiency, we introduce Monte Carlo exploration, which stochastically perturbs router probabilities so every teacher and student expert is sampled without enlarging the search space. Second, to correct routing imbalance and avert load collapse, we propose an entropy-aware router distillation mechanism that aligns the student router with the teacher while curbing over-concentration. Experiments show that B-Distill outperforms baselines by up to 6.6% in Rouge-L.

Mixture of experts (MoE) dynamically routes inputs to specialized expert networks to scale model capacity with low inference overhead. However, the excessive parameter growth in MoE models poses challenges in low-resource settings. To address these issues, MoE with parameter-efficient fine-tuning (PEFT) methods have emerged as a lightweight adaptation paradigm that distributes knowledge among experts via multiple LoRA blocks. Existing MoE-PEFT methods can be broadly categorized into External and Internal PEFT methods. External PEFT methods incorporate lightweight models into existing MoE architectures without modifying their routing, which limits the model’s parameter efficiency. To overcome these issues, Internal PEFT methods integrate MoE architectures into PEFT, enabling minimal parameter overhead. However, they still face two major challenges: (1) lack of expert functional differentiation, resulting in overlapping specialization across modules, and (2) absence of a structured attribution mechanism to guide expert selection based on semantic relevance. To alleviate these challenges, we propose TopicLoRA, a novel three-stage framework that leverages topic knowledge as semantic anchors to guide expert allocation. Specifically, (1) to address expert redundancy, we construct a topic-level prior graph using Graph Neural Network-enhanced representation learning over Big-Bench categories, enforcing structural separation among expert embeddings, and (2) to introduce semantic attribution, we design a dual-loss training mechanism that softly aligns input-query relevance with topic-guided routing distributions via KL divergence. Extensive experiments on representative datasets (e.g., MMLU, GSM8K, Flanv2) demonstrate that TopicLoRA outperforms state-of-the-art PEFT baselines by 2.40% on average in accuracy. Notably, the maximum improvement is 4.21%. Furthermore, ablation studies demonstrate that our framework's robustness to intricate topics and input sequence variations, which stems from the dual-loss training mechanism.

Large Language Models (LLMs) have demonstrated strong capabilities across diverse tasks under the example-driven learning paradigm. However, in high-stakes domains such as emergency response and industrial safety, historical incidents are scarce, confidential, or both, while concise rule books are abundant. We formalize this underexplored setting as rule knowledge-driven reasoning and ask: Can LLMs reason reliably when rules are plentiful but examples are nearly absent? To study this question, we introduce RULER, an automatic benchmark that generates 32K rigorously verified questions from 1K expert-curated emergency response rules to probe three core abilities: rule memorization, single-rule application, and multi-rule complex reasoning. RULER is further equipped with a hallucination-aware evaluation suite and novel relational metrics. A comprehensive empirical study of five representative LLMs and five enhancement strategies shows that, even when models achieve reliable performance on rule memorization and single-rule application, multi-rule complex reasoning plateaus at 5.4 on a 10-point scale. To address this limitation, we propose RAMPS, a Rule knowledge-Aware Monte Carlo Tree Search Process-reward Supervision framework. RAMPS injects rule knowledge priors into MCTS, distills 12K step-level traces without human annotation, and trains an advantage-based reward model that scores candidate reasoning paths during beam search inference. Experimental results show that RAMPS significantly improves multi-rule complex reasoning performance to 7.7.

Relation extraction (RE) identifies semantic relations between entities in text, with existing methods falling into two main paradigms: discriminative and generative.Discriminative models encode sentences and entities into relation representations and classify the most likely relation, whereas generative models directly produce relation labels through sequence generation.Although the latter have benefited from recent advances in large language models (LLMs), their performance remains limited by bottlenecks.In this work, we present the systematic investigation of how discriminative models can support generative RE.We propose the Discriminative-to-Generative (D2G) framework, which first leverages discriminative models to produce a top-k set of candidate relations, and then integrates this knowledge into generative models via in-context or prompt learning.Extensive experiments on five benchmarks demonstrate that D2G consistently achieves state-of-the-art performance, with notable gains on long-tailed relation classes.

Existing knowledge graphs (KGs) inevitably contain outdated or erroneous knowledge that needs to be removed from knowledge graph embedding (KGE) models. To address this challenge, knowledge unlearning can be applied to eliminate specific information while preserving the integrity of the remaining knowledge in KGs. Existing unlearning methods can generally be categorized into exact unlearning and approximate unlearning. However, exact unlearning requires high training costs, while approximate unlearning faces two issues when applied to KGs due to the inherent connectivity of triples: (1) It fails to fully remove targeted information, as forgetting triples can still be inferred from remaining ones. (2) It focuses on local data for specific removal, which weakens the remaining knowledge in the forgetting boundary. To address these issues, we propose GraphDPO, a novel approximate unlearning framework based on direct preference optimization (DPO). Firstly, to effectively remove forgetting triples, we reframe unlearning as a preference optimization problem, where the model is trained by DPO to prefer reconstructed alternatives over the original forgetting triples. This formulation penalizes reliance on forgettable knowledge, mitigating incomplete forgetting caused by KG connectivity. Moreover, we introduce an out-boundary sampling strategy to construct preference pairs with minimal semantic overlap, weakening the connection between forgetting and retained knowledge. Secondly, to preserve boundary knowledge, we introduce a boundary recall mechanism that replays and distills relevant information both within and across time steps. We construct eight unlearning datasets across four popular KGs with varying unlearning rates. Experiments show that GraphDPO outperforms state-of-the-art baselines by up to 10.1% in MRR_Avg and 14.0% in MRR_F1. Further analysis confirms that GraphDPO more effectively removes target knowledge while preserving surrounding context.

Ziyu Shang, Jianghan Liu, Zhizhao Luo, Peng Wang, Wenjun Ke, Jiajun Liu, Zijie Xu, Guozheng Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Knowledge graph reasoning (KGR) seeks to infer new factual triples from existing knowledge graphs (KGs). Recent methods have unified transductive and inductive reasoning by learning entity-independent representations through local neighboring structures. Nevertheless, these methods often encounter inefficiencies and rely on elaborate local structures without directly modeling the correlations between queries and various structures within KGs. In this paper, we propose a novel framework MulGA, which is designed to learn multi-granularity and adaptive embeddings for KGR. MulGA first employs connectivity subgraphs to uniformly and hierarchically represent query-related structures within KGs, such as triples, relation paths, and subgraphs, establishing the hierarchical relationship between structures at different granularities. Subsequently, we design a graph neural network-based multi-granularity embedding propagation module that unifies the message-passing process with the connectivity subgraph construction. This module obtains the query-related structural representations by all entities at multiple granularities, eliminating the need to explicitly extract any graph elements, thus addressing inefficiency issues. Moreover, we develop a structure-aware adaptive merging mechanism that assigns weights to different granularities and integrates them into cohesive subgraph-granularity representations for reasoning. The systematic experiments have been conducted on 15 benchmarks and MulGA achieves a significant improvement in MRR by an average of 0.5%-1.1% on transductive tasks and 0.2%-7.3% on inductive tasks than existing state-of-the-art methods. Moreover, MulGA exhibits faster convergence speed, smaller number of parameters, competitive inference time, and alleviates the over-smoothing prevalent in graph neural networks.

The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (TableIE) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I^2CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples. Specifically, we first adopt off-the-shelf LLMs to perform schema-agnostic pre-extraction of triples in unlabeled samples using TableIE. Then we propose a novel triple-level similarity metric considering triple semantics between these samples and train a sample retrieval model based on calculated similarities in pre-extracted unlabeled data. We also devise three different sample annotation strategies for various scenarios. Finally, the annotated samples are considered as few-shot demonstrations in ICL for RTE. Experimental results on two RTE benchmarks show that I^2CL with TableIE achieves state-of-the-art performance compared to other methods under various few-shot RTE settings.

Extracting structured event knowledge, including event triggers and corresponding arguments, from military texts is fundamental to many applications, such as intelligence analysis and decision assistance. However, event extraction in the military field faces the data scarcity problem, which impedes the research of event extraction models in this domain. To alleviate this problem, we propose CMNEE, a large-scale, document-level open-source Chinese Military News Event Extraction dataset. It contains 17,000 documents and 29,223 events, which are all manually annotated based on a pre-defined schema for the military domain including 8 event types and 11 argument role types. We designed a two-stage, multi-turns annotation strategy to ensure the quality of CMNEE and reproduced several state-of-the-art event extraction models with a systematic evaluation. The experimental results on CMNEE fall shorter than those on other domain datasets obviously, which demonstrates that event extraction for military domain poses unique challenges and requires further research efforts. Our code and data can be obtained from https://github.com/Mzzzhu/CMNEE. Keywords: Corpus,Information Extraction, Information Retrieval, Knowledge Discovery/Representation