Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process.This isolation leads to a fundamental misalignment: documents identified as topically relevant by information retrieval metrics often fail to provide the actual utility required by the LLM for precise answer generation.To bridge this gap, we introduce ReRanking Preference Optimization (RRPO) 1 , a reinforcement learning framework that directly aligns reranking with the LLM's generation quality.By formulating reranking as a sequential decision-making process, RRPO optimizes for context utility using LLM feedback, thereby eliminating the need for expensive human annotations.To ensure training stability, we further introduce a reference-anchored deterministic baseline.Extensive experiments on knowledge-intensive benchmarks demonstrate that RRPO significantly outperforms strong baselines, including the powerful list-wise reranker RankZephyr.Further analysis highlights the versatility of our framework: it generalizes seamlessly to diverse readers (e.g., GPT-4o), integrates orthogonally with query expansion modules like Query2Doc, and remains robust even when trained with noisy supervisors.

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, yet they often suffer from hallucinations and lack reliable factual grounding. Meanwhile, knowledge graphs (KGs) provide structured factual knowledge, but lack the flexible reasoning abilities of LLMs. In this paper, we present Reason-Align-Respond (RAR), a novel framework that systematically integrates LLM reasoning with knowledge graphs for knowledge graph question answering (KGQA). Our approach consists of three key components: a Reasoner that generates human-like natural language reasoning chains, an Aligner that maps these chains to valid KG paths, and a Responser that synthesizes the final answer. We formulate this process as a latent variable mixture model and optimize it using the Expectation-Maximization algorithm, which iteratively refines the reasoning chains and knowledge paths. Extensive experiments on multiple benchmarks demonstrate the effectiveness of RAR, achieving state-of-the-art performance with Hit scores of 93.3% and 91.0% on WebQSP and CWQ respectively. Human evaluation confirms that RAR generates high-quality, interpretable reasoning chains well-aligned with KG paths while maintaining computational efficiency during inference.

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts.We propose ChainEdit, a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates.By automatically extracting logical patterns from structured knowledge bases and aligning them with LLMs' internal logics, ChainEdit dynamically generates and edits logically connected knowledge clusters.Experiments demonstrate an improvement of more than 30% in logical generalization over baselines while preserving editing reliability and specificity.We further address evaluation biases in existing benchmarks through knowledge-aware protocols that disentangle external dependencies.This work establishes new state-of-the-art performance on ripple effect while ensuring internal logical consistency after knowledge editing.The code is available at https://github.com/NUSTM/ChainEdit.

Despite growing interest in emotion cause analysis in conversations, existing research is limited by the small scale of available datasets, with the largest benchmarks containing only around 1,000 conversations. This inadequacy poses significant challenges for training effective models and conducting reliable evaluations. Moreover, traditional benchmarks' definition of emotion causes as singular, continuous spans fails to capture the complex nature of conversational emotions, where causes are often scattered across multiple utterances. To address these limitations, we construct the Emotion Cause of DailyDialog (ECDaily), a large-scale dataset containing 13,118 conversations and 102,970 utterances - ten times larger than existing ones. ECDaily uniquely incorporates both individual and aggregated cause span annotations. In addition to the Individual-ECE and Individual-ECPE tasks, we introduce two new tasks - Aggregated-ECE and Aggregated-ECPE - along with a two-stage approach for handling multiple-span causes. We establish five baseline systems using several pre-trained language models for both individual and aggregated tasks. Extensive experiments demonstrate the effectiveness of the baselines trained on ECDaily across multiple tasks, and indicate that ECDaily serves as a robust and comprehensive benchmark for advancing emotion cause analysis in conversations. The dataset and source code will be publicly available at:https://github.com/NUSTM/ECDaily.

Emotion cause analysis has attracted increasing attention in recent years. However, the integration of multimodal information with emotion causes remains underexplored. Existing studies merely extract utterances from conversations as cause evidence, which is too coarse-grained to locate the exact causes from other modalities, especially those that may be reflected only in a specific video frame of an utterance. To address these limitations, we introduce a new task named Multimodal Emotion Cause Generation in Conversations (MECGC), which aims to generate an abstractive summary clearly and intuitively describing the causes that trigger the given emotion based on the multimodal context of conversations. We accordingly construct a dataset named ECGF that contains 1,374 conversations and 7,690 emotion instances from TV series. We further develop a generative framework that first generates emotion-cause aware video captions (Observe) and then facilitates the generation of emotion causes (Generate). The captioning model is trained with examples synthesized by a Multimodal Large Language Model (MLLM). Experimental results demonstrate the effectiveness of our framework and the significance of multimodal information for emotion cause analysis. Our dataset and source codes are available at https://github.com/NUSTM/MECGC.

ATOMIC is a large-scale commonsense knowledge graph (CSKG) containing everyday ifthen knowledge triplets, i.e., {head event, relation, tail event}.The one-hop annotation manner made ATOMIC a set of independent bipartite graphs, which ignored the numerous links between events in different bipartite graphs and consequently caused shortages in knowledge coverage and multi-hop paths.In this work, we aim to construct Dense-ATOMIC with high knowledge coverage and massive multi-hop paths.The events in ATOMIC are normalized to a consistent pattern at first.We then propose a CSKG completion method called Rel-CSKGC to predict the relation given the head event and the tail event of a triplet, and train a CSKG completion model based on existing triplets in ATOMIC.We finally utilize the model to complete the missing links in ATOMIC and accordingly construct Dense-ATOMIC.Both automatic and human evaluation on an annotated subgraph of ATOMIC demonstrate the advantage of Rel-CSKGC over strong baselines.We further conduct extensive evaluations on Dense-ATOMIC in terms of statistics, human evaluation, and simple downstream tasks, all proving Dense-ATOMIC's advantages in Knowledge Coverage and Multi-hop Paths.Both the source code of Rel-CSKGC and Dense-ATOMIC are publicly available on https://github.com/ NUSTM/Dense-ATOMIC.