Jianxiang Peng
5 papers · 2025–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer π Cross-Pollinator (15)
β
The Questioner
Conferences
ACL (3)
EMNLP (2)
Top co-authors
Keywords
large language model
(3)
instruction tuning
(2)
ai safety
(1)
monte carlo tree search
(1)
low-resource language
(1)
generative model
(1)
pairwise comparison
(1)
mixture of expert
(1)
controllable generation
(1)
continual pre-training
(1)
context window
(1)
length extrapolation
(1)
length generalization
(1)
dialogue system
(1)
action planning
(1)
ethical reasoning
(1)
rotary positional embedding
(1)
multi-agent system
(1)
evaluation criterion
(1)
ethical principle
(1)
Papers
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan
ACL 2026
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria
ACL 2025
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
ACL 2025
DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?
EMNLP 2025
DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search
EMNLP 2025