15 papers
Aligning LLMs with Sparse Retrieval via Adaptive Sparse Supervision
Tongna Chen, Minghan Li, Guodong Zhou
While large language models (LLMs) offer strong semantic representations, their application to first-stage retrieval incurs substantial latency and storage costs. Neural sparse ret…
XViewRank: Overlap-Conditioned Score Fusion for LLM-Augmented Sparse Retrieval
Xinxuan Lv, Minghan Li, Guodong Zhou
Large language models can reduce vocabulary mismatch in sparse retrieval by generating alternative views of a query. Once these views are searched independently, however, their ran…
Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs
Minghan Li, Guodong Zhou
Visible reasoning traces of Chinese reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets. We ask whether…
S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
Minghan Li, Junjie Zou, Xinxuan Lv +2
Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what…
GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval
Minghan Li, Tianrui Lv, Chao Zhang +1
The semantic gap between colloquial user queries and professional legal documents presents a fundamental challenge in Legal Case Retrieval (LCR). Existing dense retrieval methods t…
NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation
Jiahang Liu, Yuanxing Duan, Jiazhao Zhang +4
Simulating realistic environments for robots is widely recognized as a critical challenge in robot learning, particularly in terms of rendering and physical simulation. This challe…
GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos
Minghan Li, Tongna Chen, Tianrui Lv +3
Existing text-to-video retrieval benchmarks often permit matching from static appearance, making it difficult to determine whether models capture state changes and final outcomes.…
Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion
Minghan Li, Guodong Zhou
Large language models have recently enabled a generative paradigm for query expansion, but their high inference cost makes direct deployment difficult in practical retrieval system…
Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion
Minghan Li, Ercong Nie, Siqi Zhao +3
Query expansion with large language models is promising but often relies on hand-crafted prompts, manually chosen exemplars, or a single LLM, making it non-scalable and sensitive t…
RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QA
Chao Zhang, Minghan Li, Tianrui Lv +1
Large language models (LLMs) often generate hallucinations in knowledge-intensive QA due to parametric knowledge limitations. While existing methods like KG-CoT improve reliability…
A Survey of Long-Document Retrieval in the PLM and LLM Era
Minghan Li, Miyang Luo, Tianrui Lv +4
The proliferation of long-form documents presents a fundamental challenge to information retrieval (IR), as their length, dispersed evidence, and complex structures demand speciali…
Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
Minghan Li, Xinxuan Lv, Junjie Zou +5
Modern information retrieval must reconcile short, ambiguous queries with increasingly diverse and dynamic corpora. Query expansion (QE) remains a core technique for mitigating voc…
Efficient Long-Document Reranking via Block-Level Embeddings and Top-k Interaction Refinement
Minghan Li, Eric Gaussier, Guodong Zhou
Dense encoders and LLM-based rerankers struggle with long documents: single-vector representations dilute fine-grained relevance, while cross-encoders are often too expensive for p…
EviRerank: Adaptive Evidence Construction for Long-Document LLM Reranking
Minghan Li, Eric Gaussier, Juntao Li +1
Decoder-only LLM rerankers struggle with long documents: inference is costly and relevance signals can be diluted by irrelevant context. Motivated by an attention analysis indicati…
Domain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labeling
Minghan Li, Eric Gaussier
Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the result…