Papers by Xiangqing Shen
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Current reranking models are optimized on static human annotations in isolation, decoupled from the downstream generation process. |
| Approach: | They propose a reinforcement learning framework that directly aligns reranking with LLM's generation quality. |
| Outcome: | Experiments on knowledge-intensive benchmarks show that RRPO outperforms strong baselines. |
Flexible Thinking for Multimodal Emotional Support Conversation via Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current Chain-of-Thought based ESC methods often employ rigid, text-only reasoning, limiting adaptability in dynamic, multimodal interactions and introducing reasoning noise that degrades support quality. |
| Approach: | They propose a framework that integrates supervised fine-tuning with reinforcement learning to improve ESC models' response quality. |
| Outcome: | The proposed framework enables models to select contextually relevant thinking aspects: Visual Scene, Emotion, Situation, and Response Strategy. |
MEMIT-Merge: Addressing MEMIT’s Key-Value Conflicts in Same-Subject Batch Editing for LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing techniques that modify models’ internal knowledge without full model retraining have gained significant attention. |
| Approach: | They propose an enhanced approach that merges value computation processes for facts sharing the same subject to improve editing efficiency. |
| Outcome: | The proposed method maintains a 98% editing success rate on same-subject and distinct-sub subject datasets while the original success rate drops to 46%. |
From Phrases to Subgraphs: Fine-Grained Semantic Parsing for Knowledge Graph Question Answering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to knowledge graph question answering (KGQA) face semantic misalignment and reasoning noise. |
| Approach: | They propose a fine-grained semantic parsing framework for KGQA that maps natural language queries to executable logical forms. |
| Outcome: | The proposed framework achieves 18.5% performance improvement over the SOTA on a multi-hop CWQ dataset. |
Interactive Semantic Parsing with Reinforcement Learning for Knowledge Graph Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve LLM reliability rely on factual hallucinations . Existing methods rely only on graph traversal, resulting in imprecise retrieval and heavy post-processing burdens. |
| Approach: | They propose a framework that integrates knowledge Graphs as structured, high-fidelity buffers to enhance LLM reliability. |
| Outcome: | The proposed framework allows logical constraints to be dynamically interleaved with graph search while optimizing via reinforcement learning with only final answer feedback eliminates the need for gold program annotations. |
Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths (2023.acl-long)
Copied to clipboard
| Challenge: | ATOMIC is a large-scale commonsense knowledge graph (CSKG) containing everyday if-then knowledge triplets, i.e., head event, relation, tail event. |
| Approach: | They propose a CSKG completion method called Rel-CSKGC to predict the relation given the head event and tail event of a triplet and train a model based on existing triplets. |
| Outcome: | The proposed method is based on existing triplets and can be used to complete the missing links in ATOMIC. |
VCD: A Dataset for Visual Commonsense Discovery in Images (2025.findings-acl)
Copied to clipboard
| Challenge: | Visual commonsense data sets lack visual grounded representations of commonsensense . existing knowledge bases lack visual-based knowledge tied to actual visual scenes . |
| Approach: | They present a large-scale visual commonsense dataset with over 100,000 images and 14 million object-commonsense pairs that integrates both Seen (directly observable) and Unseen (inferrable) commonsens. |
| Outcome: | The proposed model integrates Seen (directly observable) and Unseen (inferrable) commonsense across Property, Action, and Space aspects. |
Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clustering (2023.findings-acl)
Copied to clipboard
| Challenge: | Commonsense knowledge graphs are typically represented by short text, resulting in many different nodes representing the same concept. |
| Approach: | They propose a framework based on Contrastive Pretraining and Node Clustering to solve these problems. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two CSKG completion benchmarks. |
ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains (2025.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge editing methods for large language models struggle to maintain logical consistency when propagating ripple effects to associated facts. |
| Approach: | They propose a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates. |
| Outcome: | The proposed framework improves logical generalization and specificity while maintaining reliability and specificness. |
LoReFact: Bridging the Logic Gap in Fact-Checking (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing fact-checking methods focus on verification of individual facts, overlooking logical dependencies . a recent study shows that text containing logical errors may still be misjudged as factual . |
| Approach: | They propose a content–logic coupled factuality evaluation paradigm that conceptualizes factual dimension along two complementary dimensions: content factualism and logic factuity. |
| Outcome: | The proposed paradigm bridges the gap between factual verification and content factuality . it incorporates the logical dimension and a logic-aware metric to expose and penalize logical fallacies. |