🧑‍🔬 Haifeng Chen

🏛️ Affiliations

🏢NECIrving · United States2016–2026 · 56 paperscurrent🏢NECTokyo · Japan2020–2026 · 7 paperscurrent🏢MicrosoftRedmond · United States2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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. Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization (2023 · 141 citations)
   Earlier work on large language models for summarization mostly examined generic news summaries. This paper asks how ChatGPT performs in the harder, user-driven setting where a summary must answer a specific query or cover a given aspect. The authors tested it on four public benchmarks from different domains: QMSum…
2. Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning (2026 · 7 citations)
   Reasoning LLMs often keep producing chain-of-thought steps long after the answer is effectively settled. This "overthinking" wastes compute and can even push the model toward a wrong answer. The authors present REFRAIN, a framework that needs no training and decides at inference time when to cut reasoning short. It…
3. Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models (2026 · 2 citations)
   Large language models often carry a Western-leaning cultural bias. Existing cultural alignment methods, such as persona prompting or fine-tuning on value surveys like WVS, have two weaknesses. Broad value data transfers poorly to concrete culture-sensitive tasks such as offensive language detection. Training one…
4. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs (2026 · 1 citation)
   Once deployed, LLMs cannot easily absorb new or corrected facts. Retraining is expensive. Weight-editing methods tend to collapse as edits pile up, especially with long, free-form knowledge rather than subject–relation–object triples. The authors propose RILKE, which keeps the base model frozen and instead edits…

All works

7 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Exploring the Limits of ChatGPT for Query or Aspect-based Text SummarizationarXiv:2302.08081Xianjun Yang, Yan Li, Xinlu Zhang, et al.2023 · 141 citations
2. Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Renliang Sun, Wei Cheng, Dawei Li, et al.2026 · 7 citations
3. Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Binchi Zhang, Xujiang Zhao, Jundong Li, et al.2026 · 2 citations
4. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Xuyuan Liu, Shengyu Chen, Xinshuai Dong, et al.2026 · 1 citation
5. Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement ↗Findings of the Association for Computational Linguistics: EACL 2026 · no summary yetWangyang Ying et al.2026
6. Uncertainty-Aware Test-Time Search for Optimization Problem Solving ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetLinlin Yu et al.2026
7. LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetBinchi Zhang et al.2026

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Wei Cheng ×2
• Xujiang Zhao ×2
• Zhengzhang Chen ×2
• Dawei Li
• Haoyu Wang
• Jundong Li
• Renliang Sun
• Wei Wang
• Xianjun Yang
• Xinlu Zhang
• Yan Li

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) ×5: ACL 2026 ×3
• Findings of the Association for Computational Linguistics: EACL 2026

🔗 Cited by

Papers of our library cite their works 67 times (of the 149,439 papers whose bibliographies we read); 12 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

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