🧑‍🔬 Fengran Mo

🏛️ Affiliations

🎓Université de MontréalMontreal · Canada2022–2026 · 101 papersEducation 2022–2026 · PhD, Department of Computer Science and Operations ResearchEmployment 2022–2026 · PhD Student, DIROcurrent🎓Beijing Jiaotong UniversityBeijing · China2025–2026 · 3 paperscurrent🎓University of Notre DameNotre Dame · United States2025–2026 · 3 paperscurrent🎓Rochester Institute of TechnologyRochester · United States2026 · 2 papersEmployment since 2026 · Department of Computer Sciencecurrent🎓Tsinghua UniversityBeijing · China2026 · 2 paperscurrent🏢SalesforceSan Francisco · United States2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions 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. Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation (2026 · 5 citations)
   The paper addresses two problems in multilingual retrieval-augmented generation (MRAG). The first is knowledge bias: an LLM answers the same question differently depending on its language. The second is knowledge conflict: passages retrieved from collections in many languages contradict each other. The authors…
2. Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer (2026 · 3 citations)
   Tree-like and multi-chain prompting methods such as ToT usually refine or extend reasoning paths the model has already produced.
3. Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026 · 2 citations)
   Multi-turn conversational search is usually handled by a fixed "rewrite, retrieve, generate" chain of separately trained components.
4. Instant Personalized Large Language Model Adaptation via Hypernetwork (2026 · 2 citations)
   Tailoring LLMs to individual users with parameter-efficient fine-tuning works well. However, the "One-PEFT-Per-User" (OPPU) approach trains a separate adapter for every person, which is too costly for millions of users or for preferences that change over time. The authors propose Profile-to-PEFT (P2P), which replaces…
5. MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues (2026 · 1 citation)
   Most safety benchmarks for multimodal large language models (MLLMs) test one image–prompt pair at a time. They miss harmful intent that builds up over a conversation or that is stated early and then hidden behind innocent follow-ups. MTMCS-Bench fills this gap with three-turn dialogues grounded in COCO-style images.…
6. ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting (2026 · 1 citation)
   Attention-based re-ranking scores candidate documents from an LLM's internal attention rather than from generated output.
7. When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life (2026 · 1 citation)
   Multimodal LLMs are increasingly used as everyday assistants. Their answers can steer people into risky actions even when the user has no harmful intent. Most existing safety benchmarks target jailbreaks or explicit harm, and implicit-risk sets tend to be small or artificial. The authors introduce SaLAD, a benchmark…
8. A Dual-View Analysis of Multiple Languages in Colonial Newspapers (2026)
   Colonial-era newspapers record how racial categories were built and maintained, but they are hard to analyse computationally. Annotated data is scarce, OCR output is noisy, and the texts are multilingual and archaic. The authors study racialization from two complementary angles.

All works

9 works of theirs in our library, the most cited first; 8 with a page here, the others link their original until we summarise them.

1. Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search ↗Findings of the Association for Computational Linguistics: EMNLP 2023 · no summary yetKelong Mao et al.2023 · 99 citations
2. Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented GenerationFindings of the Association for Computational LinguisticsRui Qi, Fengran Mo, Yufeng Chen, et al.2026 · 5 citations
3. Blind Spot Navigation in Large Language Model Reasoning with Thought Space ExplorerFindings of the Association for Computational LinguisticsJinghan Zhang, Fengran Mo, Tharindu Cyril Weerasooriya, et al.2026 · 3 citations
4. Agentic Conversational Search with Contextualized Reasoning via Reinforcement LearningFindings of the Association for Computational LinguisticsFengran Mo, Yifan Gao, Sha Li, et al.2026 · 2 citations
5. Instant Personalized Large Language Model Adaptation via HypernetworkAnnual Meeting of the Association for Computational Linguistics (ACL)Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, et al.2026 · 2 citations
6. MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn DialoguesFindings of the Association for Computational LinguisticsZheyuan Liu, Dongwhi Kim, Yixin Wan, et al.2026 · 1 citation
7. ReAttn: Improving Attention-based Re-ranking via Attention Re-weightingFindings of the Association for Computational LinguisticsYuxing Tian, Fengran Mo, Weixu Zhang, et al.2026 · 1 citation
8. When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily LifeFindings of the Association for Computational LinguisticsXinyue Lou, Xu Jinan, Jingyi Yin, et al.2026 · 1 citation
9. A Dual-View Analysis of Multiple Languages in Colonial NewspapersFindings of the Association for Computational LinguisticsZhan Su, Xiaoya Chen, Fengran Mo, et al.2026

🤝 Co-authors here

12 of 36 co-authors with a page, the most papers together first.

• Meng Jiang ×4
• Zhaoxuan Tan ×3
• Jian-Yun Nie ×2
• Kaiyu Huang ×2
• Xu Jinan ×2
• Zheyuan Liu ×2
• Dakuo Wang
• Dongjie Wang
• Hansi Zeng
• Haoyang Wen
• Jianshu Chen
• Jinghan Zhang

Venues

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

• Findings of the Association for Computational Linguistics ×7: Findings of the Association for Computational Linguistics 2026 ×7
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• Findings of the Association for Computational Linguistics: EMNLP 2023

🔗 Cited by

Papers of our library cite their works 57 times (of the 149,439 papers whose bibliographies we read); 13 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/fengran-mo/