Searcharxiv⌕ Search

arXiv subjects

Guodong Zhou

Publications and source records attributed to Guodong Zhou.

At least 19 recordsLinked to original sources
arXiv2026

Aligning LLMs with Sparse Retrieval via Adaptive Sparse Supervision

While large language models (LLMs) offer strong semantic representations, their application to first-stage retrieval incurs substantial latency and storage costs. Neural sparse retrievers such as SPLADE provide efficient retrieval but rely on relatively compact encoders with limited representational capacity. To bridge this gap, we propose an LLM-based sparse retrieval framework with input-adaptive sparse alignment. Specifically, we introduce a dynamic $α$-truncation strategy that selects input-specific supervision supports based on the cumulative activation mass of SPLADE representations. This strategy guides the LLM to preserve salient lexical signals while suppressing less informative activations, without relying on a fixed support budget. Subsequent retrieval fine-tuning combines contrastive learning, knowledge distillation, and sparsity regularization to improve retrieval effectiveness. Experiments on MS MARCO and six selected BEIR datasets demonstrate improvements over SPLADE++ while maintaining competitive effectiveness against LLM-based sparse retrievers. Compared with Lion-sp, our method reduces index storage by 6.4-fold and end-to-end query latency by over 11-fold, achieving a favorable effectiveness-efficiency trade-off.

cs.IR↗
arXiv2026

EviRerank: Adaptive Evidence Construction for Long-Document LLM Reranking

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 indicating a consistent degradation trend when non-relevant text is appended, we propose EviRerank, an evidence-based long-document reranking framework for decoder-only LLMs. EviRerank (i) scores document blocks with a lightweight selector (BM25, bi-encoder, or cross-encoder), (ii) constructs a compact reranking context under a hard token cap by dynamically budgeting evidence blocks with Adaptive Evidence Budgeting (AEB) and adding a global summary cue via Summary Augmentation (SA), and (iii) reranks with a decoder-only LLM. Across TREC DL'19, DL'22, DL'23, and MLDR-zh, EviRerank consistently outperforms full-document LLM reranking and strong block-selection baselines while substantially reducing the required input length. On TREC DL'19, EviRerank reaches up to 0.744 nDCG@10 while substantially reducing reranking latency. Additional RankZephyr-7B experiments confirm transfer to listwise reranking under matched context budgets.

cs.IR↗
arXiv2026

GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos

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. We introduce GenState-AI, a benchmark comprising 956 AI-generated videos and 195 verified state-change queries across Toy, Cartoon, Home, and Manipulation domains. Its construction uses prompt-controlled variants that target either conflicting temporal/state outcomes or semantic substitutions. Following human verification, all valid videos contribute to subset-level retrieval pools, while complete query-specific triplets support diagnostic hard-negative ordering. We evaluate VCF-Lik, Qwen3-VL, and LanguageBind using both standard Recall@K and triplet-based consistency metrics. Qwen3-VL (8B) achieves the best macro-average R@1 and triplet consistency, while LanguageBind obtains the highest semantic discrimination accuracy. However, stronger retrieval does not consistently yield correct hard-negative ordering, and Qwen3-VL and LanguageBind remain weak on Manipulation triplets, where VCF-Lik performs substantially better. GenState-AI therefore provides a controlled diagnostic testbed for distinguishing global retrieval quality from fine-grained temporal and semantic grounding in AI-generated videos.

cs.CV↗
arXiv2026

Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs

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 the linguistic register of reasoning can be used to improve efficiency. We propose Wenyan Thinking, which emits intermediate reasoning in Classical Chinese (wenyanwen) while retaining a short direct-answer output. Starting from modern-Chinese reasoning traces, we rewrite only the reasoning field into wenyan and fine-tune Qwen3-4B-Thinking-2507 on the rewritten supervision. To distinguish register shift from generic compression, we construct a compact modern-Chinese control using the same source data, teacher family, base model, and SFT recipe. Across budget-sensitive evaluations on MMLU-ProX-Lite-ZH, CEVAL, and AGIEval-CN, Wenyan Thinking substantially reduces reasoning length and missing-answer rates under constrained decoding. Compact rewriting explains much of the efficiency gain, while wenyan consistently outperforms the compact modern-Chinese control on the primary benchmark and remains competitive across the additional benchmarks. These results identify linguistic register as a practical design axis for efficient visible reasoning in Chinese LLMs.

cs.CL↗
arXiv2026

XViewRank: Overlap-Conditioned Score Fusion for LLM-Augmented Sparse Retrieval

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 ranked lists may be complementary, redundant, or affected by query drift, making fixed fusion suboptimal. We present XViewRank, a lightweight retrieval-side method for conditionally fusing BM25 results from an original query, a hypothesis view, and a step-back view. For each pooled candidate, XViewRank retains three normalized BM25 scores and three query-level overlaps between the retrieved result sets. A small nonlinear scorer uses the overlaps as context that changes how the view-specific scores are interpreted, without jointly encoding query and passage text. Under a matched-input protocol, XViewRank improves nDCG@10 and MAP numerically over reciprocal rank fusion on both TREC DL 2019 and 2020, with a statistically significant MAP gain on DL19. Additional analyses show that the clearest benefit occurs when the view rankings have low agreement, while the evidence on DL20 is weaker. The results support overlap-conditioned score fusion as a compact retrieval-side alternative to fixed fusion, while also delimiting where its advantage is empirically established.

cs.IR↗
arXiv2026

Gerstenhaber algebra structure on the Hochschild cohomology ring of the Xu--Snashall algebra

Let $A$ be a finite dimensional algebra and let $\rmHH^*(A)$ be its Hochschild cohomology ring, which is a Gerstenhaber algebra. Denote by $\calN$ (resp. $G$, $\calG$) the ideal (resp. weak Gerstenhaber ideal, Gerstenhaber ideal) generated by all homogeneous nilpotent elements. Motivated by their work on support varieties via Hochschild cohomology, Snashall and Solberg conjectured that $\rmHH^*(A)/\calN$ is a finitely generated algebra. Xu constructed a counterexample to the Snashall-Solberg conjecture over a base field of characteristic two, and Snashall generalized this example to arbitrary characteristic. Hermann further asked whether $\rmHH^*(A)/G$ is a finitely generated algebra and suggested considering first the Xu--Snashall algebra. In this paper, we answer this question for the Xu--Snashall algebra. In fact, by explicitly computing the Gerstenhaber algebra structure on the Hochschild cohomology ring, we show that $G=\calN$; hence $\rmHH^*(A)/G=\rmHH^*(A)/\calN$ is not a finitely generated algebra. Furthermore, we show that $\rmHH^*(A)/\calG\cong K$. Therefore, one may ask whether, for a finite dimensional algebra $A$, $\rmHH^*(A)/\calG$ is always a finitely generated algebra. Our main tools are two-sided Anick resolutions and weak self-homotopies.

math.KT↗
arXiv2026

Relative Time Intervals Representation for Word-level Timestamping with Masked Training

Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored. Our work addresses this gap by enabling SpeechLLMs to jointly model speech content and temporal structure, effectively transforming them from ``content understanding machines" into ``temporal-aware content understanding machines". Specifically, we replace traditional absolute timestamps with relative timestamps, achieving a more compact vocabulary and stronger generalization capabilities. To efficiently infuse timestamp prediction ability into pre-trained large language models, we introduce a hybrid fine-tuning strategy: full-parameter fine-tuning of the timestamp-augmented embedding layer and language model head, combined with LoRA fine-tuning of the decoder layers. Moreover, we design a masked timestamp training objective, preventing the model from over-relying on ground-truth timestamps, and thereby enhancing robustness against noisy real-world annotations. Extensive experiments demonstrate that our approach achieves significant improvements in timestamp prediction accuracy while maintaining strong speech transcription performance.

cs.AI↗
arXiv2026

Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding

While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Existing speech QA paradigms and state-of-the-art Speech LLMs suffer from acoustic information loss and poor long-term context memory. To address these issues, we construct the LongAudioQA dataset and propose the GRGA model, which models heterogeneous audio features into a multi-dimensional graph and leverages agent planning for retrieval and answer generation.

cs.SD↗
arXiv2026

Ştefan spectral sequence for faithfully flat Hopf Galois extensions is multiplicative

Let $H$ be a Hopf algebra with a bijective antipode over a field $\mathbf k$ and $B/A$ be a flat right $H$-Galois extension. Ştefan constructed a spectral sequence converging to the Hochschild cohomology $\mathrm{HH}^{p+q}(B, N)$ with $\mathrm{E}_2^{p,q} = \mathrm{H}^p(H, \mathrm{HH}^q(A, N))$. We show that when $B/A$ is faithfully flat, the Ştefan spectral sequence is multiplicative. More precisely, a new formalism of functorial multiplicative spectral sequences via lax monoidal functors over monoidal categories is introduced. A functorial multiplicative spectral sequence is constructed for any faithfully flat Hopf Galois extension. Identification with Ştefan's spectral sequence from the $E_2$-page follows from Künzer's comparison theorems. Applications include strongly graded algebras, smash products, crossed products, group and Lie algebra extensions, with new multiplicativity results in several cases.

math.RA↗
arXiv2026

A Symmetric Counterexample to the Snashall--Solberg Conjecture

It is shown that the trivial extension of the Xu--Snashall algebra is a symmetric counterexample to the Snashall--Solberg conjecture, which states that the Hochschild cohomology ring of a finite-dimensional algebra modulo nilpotence is a finitely generated algebra. To the best of our knowledge, this is the first known selfinjective counterexample.

math.KT↗
arXiv2026

Deformations and homotopy theory of Rota-Baxter Lie algebras

For Rota-Baxter Lie algebras, a homotopy cooperad is exhibited, whose cobar construction is shown to be the minimal model of the operad of Rota-Baxter Lie algebras by using algebraic Morse theory. The deformation complex of Rota-Baxter Lie algebras as well as the $L_\infty$-algebra structure on this complex are deduced from the minimal model and the notion of homotopy Rota-Baxter Lie algebras is given as a consequence.

math.KT↗
arXiv2026

Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey

Modern information retrieval must reconcile short, ambiguous queries with increasingly diverse and dynamic corpora. Query expansion (QE) remains a core technique for mitigating vocabulary mismatch, but its design space has been reshaped by pre-trained and large language models (PLMs/LLMs). This survey reviews QE methods in the PLM/LLM era and provides a unified view of the emerging landscape. We first summarize how different model families enable new expansion behaviors, including stronger contextualization, more controllable generation, and instruction-following. We then organize recent techniques along four complementary design dimensions: where expansion is injected in the pipeline, how it is grounded and interacts with corpus evidence, how it is learned or aligned, and how structured knowledge such as knowledge graphs is incorporated. Beyond taxonomy, we synthesize application patterns and deployment considerations across representative retrieval settings, highlighting practical trade-offs among effectiveness, controllability, grounding quality, and operating cost. Finally, we outline open challenges and future directions toward more reliable, safe, efficient, and continually adaptive QE under real-world constraints.

cs.IR↗
arXiv2026

GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval

The semantic gap between colloquial user queries and professional legal documents presents a fundamental challenge in Legal Case Retrieval (LCR). Existing dense retrieval methods typically treat LCR as a black-box semantic matching process, neglecting the explicit juridical logic that underpins legal relevance. To address this, we propose GLIER (Generative Legal Inference and Evidence Ranking), a framework that reformulates retrieval as an inference process over latent legal variables. GLIER decomposes the task into two interpretability-driven stages. First, a Joint Generative Inference module translates raw queries into latent legal indicators, including charges and legal elements, using a unified sequence-to-sequence strategy that jointly generates charges and elements to enforce logical consistency. Second, a Multi-View Evidence Fusion mechanism aggregates generative confidence with structural and lexical signals for precise ranking. Extensive experiments on LeCaRD and LeCaRDv2 demonstrate that GLIER outperforms strong baselines such as SAILER and KELLER. Notably, GLIER exhibits strong data efficiency, maintaining robust performance even when trained with only 10% of the data.

cs.IR↗
arXiv2026

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA

Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is adequate. In practice, systems may answer from incomplete evidence chains, or they may accumulate redundant or distractor-heavy text that interferes with later retrieval and reasoning. We propose S2G-RAG (Structured Sufficiency and Gap-judging RAG), an iterative framework with an explicit controller, S2G-Judge. At each turn, S2G-Judge predicts whether the current evidence memory supports answering and, if not, outputs structured gap items that describe the missing information. These gap items are then mapped into the next retrieval query, producing stable multi-turn retrieval trajectories. To reduce noise accumulation, S2G-RAG maintains a sentence-level Evidence Context by extracting a compact set of relevant sentences from retrieved documents. Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval. Furthermore, S2G-RAG can be integrated into existing RAG pipelines as a lightweight component, without modifying the search engine or retraining the generator.

cs.IR↗
arXiv2026

Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion

Large language models have recently enabled a generative paradigm for query expansion, but their high inference cost makes direct deployment difficult in practical retrieval systems. To address this issue, a retrieval-feedback-driven distillation and preference-alignment framework is proposed to transfer retrieval-friendly expansion behavior from a strong teacher model to a compact student model. Rather than relying on few-shot exemplars at inference time, the framework first leverages two complementary types of teacher-generated expansions, produced under zero-shot and few-shot prompting conditions, as supervision signals for distillation and as candidate pools for preference construction. A retrieval-metric-driven strategy is then introduced to automatically form chosen/rejected expansion pairs according to nDCG@10 differences, and Direct Preference Optimization is applied to explicitly align generation preferences with retrieval objectives. Experiments on TREC DL19/20/21 and MIRACL-zh show that the proposed approach preserves strong retrieval effectiveness while substantially reducing inference cost. In particular, the distilled Qwen3-4B model reaches about 97% of the teacher (DeepSeek-685B) model's nDCG@10 performance on DL19, and remains effective on the Chinese MIRACL-zh benchmark, demonstrating strong practicality across both English and Chinese retrieval settings.

cs.IR↗
arXiv2026

Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion

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 to domain shift. We present an automated, domain-adaptive QE framework that builds in-domain exemplar pools by harvesting pseudo-relevant passages using a BM25-MonoT5 pipeline. A training-free cluster-based strategy selects diverse demonstrations, yielding strong and stable in-context QE without supervision. To further exploit model complementarity, we introduce a two-LLM ensemble in which two heterogeneous LLMs independently generate expansions and a refinement LLM consolidates them into one coherent expansion. Across TREC DL20, DBPedia, and SciFact, the refined ensemble delivers consistent and statistically significant gains over BM25, Rocchio, zero-shot, and fixed few-shot baselines. The framework offers a reproducible testbed for exemplar selection and multi-LLM generation, and a practical, label-free solution for real-world QE.

cs.IR↗
arXiv2026

The Hochschild cohomlogy ring of a self-injective Nakayama algebra is a Batalin-Vilkovisky algebra

Lambre, Zhou and Zimmermann showed that the Hochschild cohomology ring of a Frobenius algebra with semisimple Nakayama automorphism is a Batalin-Vilkovisky algebra. They asked whether the semisimplicity condition is necessary. In this paper, we show that for a self-injective Nakayama algebra, the Hochschild cohomology ring is always a Batalin-Vilkovisky algebra. In course of proofs, we correct some inaccuracies in the literature, hoping not to introduce new errors.

math.KT↗