---
title: "Xunliang Cai — author profile and papers — Elamur Research"
description: "Xunliang Cai, University of Science and Technology of China: 10 papers on Elamur Research (2025–2026), h-index 9 — affiliations, topics…"
canonical: "https://research.elamur.ai/free/en/authors/xunliang-cai/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xunliang-cai/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xunliang Cai

# Xunliang Cai

Xunliang Cai has 10 papers in our library, in 2025–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/); often with [Jingang Wang](https://md.research.elamur.ai/free/en/authors/jingang-wang/), [Rongxiang Weng](https://md.research.elamur.ai/free/en/authors/rongxiang-weng/), [Can Ren](https://md.research.elamur.ai/free/en/authors/can-ren/).

10 papers in our library · 2025–2026

[OpenAlex](https://openalex.org/A5068562468) · [ORCID](https://orcid.org/0000-0003-0685-9556) · [Wikidata](https://www.wikidata.org/wiki/Q131011945) · [**h-index 9**](https://openalex.org/authors/A5068562468) · [158 works](https://openalex.org/works?filter=author.id:A5068562468) · [237 citations](https://openalex.org/works?filter=author.id:A5068562468&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 10 works in our library](https://md.research.elamur.ai/free/en/authors/xunliang-cai/#papers) · [🔗 Cited 62 times in our library](https://md.research.elamur.ai/free/en/authors/xunliang-cai/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #9158](https://md.research.elamur.ai/free/en/paper-stars/page/92/#star-9158)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Xunliang+Cai) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xunliang+Cai) · [dblp](https://dblp.org/search?q=Xunliang+Cai) · [ACL Anthology](https://aclanthology.org/search/?q=Xunliang+Cai)

## Affiliations

[🏢**Meituan** Beijing · China 2021–2026 · 88 papers*current*](https://md.research.elamur.ai/free/en/companies/meituan/) · [🎓**University of Chinese Academy of Sciences** Beijing · China 2025–2026 · 6 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) · [🎓**University of Science and Technology of China** Hefei · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) · [🏛️**Chinese Academy of Sciences** Beijing · China 2025 · 2 papers](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) · [🔬**Institute of Automation** Beijing · China 2025 · 2 papers](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) · [🔬**Institute of Computing Technology** Beijing · China 2025 · 2 papers](https://md.research.elamur.ai/free/en/labs/institute-of-computing-technology/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8 The field of science this work belongs to (OpenAlex fields).[Computer Science · 10 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 9 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Artificial Intelligence · 10 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 9 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Information Systems · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Signal Processing · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · [Software · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/software/)

🧭 Topics 7 Research subjects and languages the work is about.[Language models & pretraining · 5 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Information retrieval & search · 2 works](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Dialogue systems · 1 work](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Evaluation & benchmarks · 1 work](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Question answering · 1 work](https://md.research.elamur.ai/free/en/topics/question-answering/) · [Speech & spoken language · 1 work](https://md.research.elamur.ai/free/en/topics/speech/)

## Works by year

### 2020s

[**2026** 7 papers](https://md.research.elamur.ai/free/en/authors/xunliang-cai/year/2026/) · [**2025** 3 papers](https://md.research.elamur.ai/free/en/authors/xunliang-cai/year/2025/)

## Papers

The most cited first (OpenAlex and our library).

1. **[LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/wang-2025-llms-know-what-they-need/)** *(2025 · 14 citations)* Retrieval-augmented generation (RAG) helps LLMs with outdated or missing knowledge, but multi-hop questions remain difficult.
2. **[Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs](https://md.research.elamur.ai/free/en/papers/tan-2025-too-consistent-detect-study-self/)** *(2025 · 12 citations)* LLM error detectors often treat agreement across sampled answers as a sign of correctness. This paper identifies a blind spot in that assumption: self-consistent errors , where a model gives the same wrong answer, up to semantic equivalence, in its greedy output and in all stochastic samples. The authors define these…
3. **[LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning](https://md.research.elamur.ai/free/en/papers/jiang-2025-logicpro-improving-complex-logical-reasoning/)** *(2025 · 8 citations)* Large language models often fail at multi-step logical reasoning when a task is posed in plain text, even when the same task is easy to solve with code.
4. **[MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning](https://md.research.elamur.ai/free/en/papers/fu-2026-maspo-unifying-gradient-utilization-probability/)** *(2026 · 7 citations)* RLVR methods like GRPO inherit PPO-style hard clipping, which the authors argue is poorly suited to how LLMs learn reasoning.
5. **[Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text](https://md.research.elamur.ai/free/en/papers/xu-2026-unlocking-implicit-experience-synthesizing-tool/)** *(2026 · 4 citations)* Training LLM agents for multi-turn tool use is limited by a shortage of realistic trajectories. Most existing synthesis methods start from a fixed API collection, so the data can only be as broad as that collection. The authors invert this approach. They argue that ordinary web text, such as how-to guides and…
6. **[AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation](https://md.research.elamur.ai/free/en/papers/shi-2026-aj-bench-benchmarking-agent-as/)** *(2026)* As reinforcement learning is scaled up for LLM-based agents, checking whether an agent actually did its job becomes a bottleneck.
7. **[DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding](https://md.research.elamur.ai/free/en/papers/zhou-2026-diffa-2-practical-diffusion-large/)** *(2026)* Large audio language models are mostly autoregressive. They need a lot of data and compute to scale, and their token-by-token decoding slows inference. The earlier DIFFA work showed that a diffusion LLM backbone can help audio understanding, but only at a small, proof-of-concept scale. DIFFA-2 develops this into a…
8. **[Large-Scale Diverse Synthesis for Mid-Training](https://md.research.elamur.ai/free/en/papers/zhang-2026-large-scale-diverse-synthesis-mid/)** *(2026)* Mid-training large language models often relies on synthetic question–answer data. However, existing generators mostly reformat source text into simple, uniform QA pairs, which limits both volume and variety. The authors present BoostQA, a pipeline that first diagnoses what a pre-trained model lacks and then…
9. **[LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points](https://md.research.elamur.ai/free/en/papers/zhang-2026-linkqa-synthesizing-diverse-qa-multiple/)** *(2026)* Training LLMs is increasingly limited by a shortage of diverse, high-quality data, especially across many academic disciplines.
10. **[MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks](https://md.research.elamur.ai/free/en/papers/ruan-2026-mtr-suite-framework-evaluating-synthesizing/)** *(2026)* Conversational retrieval decides which evidence a RAG system can use, but its benchmarks have two kinds of flaws.

## All works

12 works of theirs in our library, the most cited first; 10 with a page here, the others link their original until we summarise them.

1. **[From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding ↗](https://aclanthology.org/2021.acl-long.397/) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yet**Shan Wu et al.*2021 · 37 citations*
2. **[LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/wang-2025-llms-know-what-they-need/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Keheng Wang, Feiyu Duan, Peiguang Li, et al.*2025 · 14 citations*
3. **[Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs](https://md.research.elamur.ai/free/en/papers/tan-2025-too-consistent-detect-study-self/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Hexiang Tan, Fei Sun, Sha Liu, et al.*2025 · 12 citations*
4. **[LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning](https://md.research.elamur.ai/free/en/papers/jiang-2025-logicpro-improving-complex-logical-reasoning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jin Jiang, Yuchen Yan, Yang Liu, et al.*2025 · 8 citations*
5. **[MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning](https://md.research.elamur.ai/free/en/papers/fu-2026-maspo-unifying-gradient-utilization-probability/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiaoliang Fu, Jiaye Lin, Yangyi Fang, et al.*2026 · 7 citations*
6. **[Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level ↗](https://arxiv.org/abs/2605.06387) arXiv:2605.06387 · no summary yet**Nan Jia et al.*2026 · 6 citations*
7. **[Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text](https://md.research.elamur.ai/free/en/papers/xu-2026-unlocking-implicit-experience-synthesizing-tool/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zhihao Xu, Rumei Li, Jiahuan Li, et al.*2026 · 4 citations*
8. **[AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation](https://md.research.elamur.ai/free/en/papers/shi-2026-aj-bench-benchmarking-agent-as/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Wentao Shi, Yu Wang, Yuyang Zhao, et al.*2026*
9. **[DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding](https://md.research.elamur.ai/free/en/papers/zhou-2026-diffa-2-practical-diffusion-large/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, et al.*2026*
10. **[Large-Scale Diverse Synthesis for Mid-Training](https://md.research.elamur.ai/free/en/papers/zhang-2026-large-scale-diverse-synthesis-mid/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Xuemiao Zhang, Chengying Tu, Can Ren, et al.*2026*
11. **[LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points](https://md.research.elamur.ai/free/en/papers/zhang-2026-linkqa-synthesizing-diverse-qa-multiple/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xuemiao Zhang, Can Ren, Chengying Tu, et al.*2026*
12. **[MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks](https://md.research.elamur.ai/free/en/papers/ruan-2026-mtr-suite-framework-evaluating-synthesizing/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Junhao Ruan, Abudukeyumu Abudula, Bei Li, et al.*2026*

## Co-authors here

12 of 47 co-authors with a page, the most papers together first.

- [Jingang Wang](https://md.research.elamur.ai/free/en/authors/jingang-wang/) ×5
- [Rongxiang Weng](https://md.research.elamur.ai/free/en/authors/rongxiang-weng/) ×3
- [Can Ren](https://md.research.elamur.ai/free/en/authors/can-ren/) ×2
- [Chengying Tu](https://md.research.elamur.ai/free/en/authors/chengying-tu/) ×2
- [Hongfei Yan](https://md.research.elamur.ai/free/en/authors/hongfei-yan/) ×2
- [Ke Zeng](https://md.research.elamur.ai/free/en/authors/ke-zeng/) ×2
- [Xin Chen](https://md.research.elamur.ai/free/en/authors/xin-chen/) ×2
- [Xuemiao Zhang](https://md.research.elamur.ai/free/en/authors/xuemiao-zhang/) ×2
- [Bei Li](https://md.research.elamur.ai/free/en/authors/bei-li/)
- [Binbin Zheng](https://md.research.elamur.ai/free/en/authors/binbin-zheng/)
- [Cao Liu](https://md.research.elamur.ai/free/en/authors/cao-liu/)
- [Du Su](https://md.research.elamur.ai/free/en/authors/du-su/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×5: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×4, [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)
- [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/) ×4: [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) ×3
- [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/): [COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/2025/)
- [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/): [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

## Cited by

Papers of our library cite their works 62 times (of the 149,439 papers whose bibliographies we read); [19 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xunliang-cai/cited-by/).

Updated 2 November 2026