Profiles2020-2026
Deyi Xiong
Tianjin University
69Papers
56Last author
91Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers69
- From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for TibetanAuthor 17 of 17ACL 2026 · 5 citations
- Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMsAuthor 7 of 9AAAI 2026 · 2 citations
- Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity TranslationAuthor 11 of 11ACL 2026 · 2 citations
- Revisiting Entropy in Reinforcement Learning for Large Reasoning ModelsAuthor 9 of 9ACL Findings 2026 · 2 citations
- EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific DiscoveryAuthor 3 of 3ACL 2026 · 1 citation
- Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language ModelsAuthor 6 of 6ACL 2026 · 1 citation
- AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric InternalizationAuthor 4 of 4ACL 2026
- APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and InterpretationAuthor 7 of 10ACL 2026
- Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-SortsAuthor 5 of 5ACL 2026
- DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value MappingAuthor 5 of 5ACL 2026
- ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language ModelsAuthor 6 of 6ACL Findings 2026
- ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language ModelsAuthor 10 of 10ACL Findings 2026
- From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language ModelsAuthor 9 of 10ACL 2026
- MASS: Deep Research for Social Sciences with Memory-Augmented Social SimulationAuthor 2 of 2ACL Findings 2026
- Multilingual Safety Alignment via Representation-Space SeparabilityAuthor 3 of 3ICML 2026
- Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability PatchingAuthor 7 of 7ACL Findings 2026
- SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing AlignmentAuthor 12 of 12ACL Findings 2026
- TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-ExpertsAuthor 3 of 3ACL Findings 2026
- ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue AgentsAuthor 16 of 16ACL 2025 · 9 citations
- CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language ModelsAuthor 2 of 2ACL 2025 · 5 citations
- Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in MathAuthor 2 of 2ACL Findings 2025 · 5 citations
- C²RBench: A Chinese Complex Reasoning Benchmark for Large Language ModelsAuthor 4 of 4ACL Findings 2025 · 2 citations
- Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree SearchAuthor 9 of 9ACL 2025 · 2 citations
- DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor SearchAuthor 5 of 5EMNLP 2025
- DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?Author 7 of 7EMNLP 2025
- HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and DepthAuthor 10 of 10EMNLP Findings 2025
- MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine TranslationAuthor 5 of 5ACL 2025
- Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation CriteriaAuthor 9 of 9ACL 2025
- Towards a Unified Paradigm of Concept Editing in Large Language ModelsAuthor 5 of 5EMNLP 2025
- Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark RemedyAuthor 2 of 3AAAI 2024 · 66 citations
Showing the 30 most recent indexed papers.
