Department of Computer Science

Research output

Research output per year 1991 2019 2020 2021 2022 2023 2024 2025

• 231828 Scopus Citations
• 179 Scopus h-index
• 4630 RGC 21 - Publication in refereed journal
• 3694 RGC 32 - Refereed conference paper (with host publication)
• 144 RGC 51 - Patents (CityUHK)
• 142 Editorial Preface
• 596 More
  • 114 RGC 22 - Publication in policy or professional journal
  • 106 RGC 32 - Refereed conference paper (without host publication)
  • 98 RGC 12 - Chapter in an edited book (Author)
  • 64 Foreword/preface/postscript
  • 50 RGC 14 - Edited book (Editor)
  • 27 Erratum
  • 23 RGC 33 - Other conference paper
  • 20 Preprint
  • 15 RGC 44 - Performance and participation in exhibits
  • 11 Letter
  • 10 Chapter in research book/monograph/textbook (Author)
  • 9 Poster
  • 9 RGC 47 - Computer software or system
  • 8 RGC 11 - Research book or monograph (Author)
  • 8 RGC 62 - Review of books or of software (or similar publications/items)
  • 8 Comment/debate
  • 6 RGC 31A - Invited conference paper (refereed items)
  • 3 RGC 31B - Invited conference paper (non-refereed items)
  • 2 RGC 43 - Film, video
  • 1 RGC 13 - Textbook (Author)
  • 1 Abstract
  • 1 Meeting abstract
  • 1 RGC 46 - Engineering, architectural, graphic designs
  • 1 Working paper

Research output per year

Research output per year

Search results

• 2025

  Active Instruction Tuning for Large Language Models with Reference-Free Instruction Selection

  Zhang, Q., Chen , J. & Ma, C., 26 May 2025, (Accepted/In press/Filed).

  Research output: Conference Papers › RGC 31A - Invited conference paper (refereed items) › Yes › peer-review

  • Instruction Selection 100%
  • Large Language Model 100%
  • Subjective 100%
  • Experimental 100%
  • Pioneers 100%

• Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge

  Zhang, Q., Wang, Y., Jiang, Y., Li, L., Wu, C., Wang, Y., Jiang, X., Shang, L., Tang, R., Lyu, F. & Ma, C., 16 May 2025, (Accepted/In press/Filed).

  Research output: Conference Papers › RGC 31A - Invited conference paper (refereed items) › Yes › peer-review

  • Large Language Model 100%
  • Majority Voting 33%
  • Superior Performance 33%
  • Comparative Evaluation 33%
  • Average Accuracy 33%

• REVISEVAL: IMPROVING LLM-AS-A-JUDGE VIA RESPONSE-ADAPTED REFERENCES

  Zhang, Q., Wang, Y., YU, T., Jiang, Y., Wu, C., Li, L., Wang, Y., Jiang, X., Shang, L., Tang, R., Lyu, F. & Ma, C., 24 Apr 2025. 27 p.

  Research output: Conference Papers › RGC 31A - Invited conference paper (refereed items) › Yes › peer-review

  Open Access

  • Large Language Model 100%
• 2024

  Collaborative Performance Prediction for Large Language Models

  ZHANG, Q., Lyu, F., Liu, X. & Ma, C., Nov 2024, p. 2576-2596.

  Research output: Conference Papers › RGC 31A - Invited conference paper (refereed items) › Yes › peer-review

  Open Access

  File

  • Large Language Model 100%
  • Prediction Accuracy 33%
  • Online Platform 33%
  • Computational Linguistics 33%
  57 Downloads (CityUHK Scholars)
• 2016

  Social Support Seeking In Patient-centric Online Healthcare Communities

  LIU, N., Chan, H.-C., LU, Z. & TONG, Y., 12 Jun 2016.

  Research output: Conference Papers › RGC 31A - Invited conference paper (refereed items) › Yes › peer-review
• 2015

  Slope-based sequencing yardstick for analyzing unsatisfactory performance of multithreaded programs

  Chan, W. K., Tse, T. H., Wu, S., Yu, Y. T. & Zhang, Z., 1 Jul 2015, p. 11-16.

  Research output: Conference Papers › RGC 31A - Invited conference paper (refereed items) › Yes › peer-review

  1 Citation (Scopus)