🧑‍🔬 Zhiwei Liu

🏛️ Affiliations

🎓University of ManchesterManchester · United Kingdom2024–2026 · 29 papersEducationcurrent

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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025 · 68 citations)
   Open-source LLMs lag behind proprietary systems on agent tasks such as tool use. A major cause is that public agent datasets are scarce, inconsistent in format, homogeneous in content, and often noisy, with problems like hallucinated actions or repeated turns. The authors (Salesforce AI) release xLAM, a family of…
2. APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay (2025 · 36 citations)
   Building capable multi-turn AI agents requires training data that captures realistic exchanges between humans and agents.
3. DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI (2023 · 21 citations)
   Conversational models often struggle across varied dialogue tasks because training data is fragmented, small, task-specific and stored in inconsistent formats.
4. Selective Preference Optimization via Token-Level Reward Function Estimation (2025 · 8 citations)
   Token-level preference alignment for LLMs usually trains on every token, which adds noise and wastes compute.
5. Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026 · 2 citations)
   LLMs are increasingly used to judge financial claims, but existing benchmarks such as FinFact and FinDVer test verification in one fixed setting.
6. Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026 · 1 citation)
   Continual pre-training of an LLM on a narrow target field, such as math, often causes catastrophic forgetting of general skills.
7. MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model (2026)
   False or manipulated financial content is hard to detect because it often hides in small numerical edits, exaggerated sentiment or inverted cause–effect claims.
8. RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models (2026)
   Large reasoning models (LRMs) can produce fluent chains of thought that still hide small arithmetic slips or broken constraints, which then lead to wrong final answers.
9. Towards Scalable Lightweight GUI Agents via Multi-role Orchestration (2026)
   Multimodal LLM agents that operate phone and desktop interfaces work best at large scale, but such models are too costly to run on end-user devices.

🤝 Co-authors here

12 of 49 co-authors with a page, the most papers together first.

• Jianguo Zhang ×3
• Shelby Heinecke ×3
• Fang Zhouhua ×2
• Jimin Huang ×2
• Juan Carlos Niebles ×2
• Kailai Yang ×2
• Ming Zhu ×2
• Sophia Ananiadou ×2
• Thai Hoang ×2
• Tianlei Zhu ×2
• Weiran Yao ×2
• Yong Li ×2

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) ×3: ACL 2026 ×2
• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×2, Findings of the Association for Computational Linguistics 2023
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Workshop on Multilinguality in the Era of Large Language Models: Workshop on Multilinguality in the Era of Large Language Models 2026
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2025
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025

🔗 Cited by

Papers of our library cite their works 112 times (of the 149,439 papers whose bibliographies we read); 31 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhiwei-liu/