Profiles2021-2026
Xiting Wang
Renmin University of China
20Papers
3Last author
39Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers20
- Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model EvaluatorAuthor 2 of 6ICLR 2026 · 11 citations
- DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative WritingAuthor 6 of 9ACL 2026 · 3 citations
- ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series ForecastingAuthor 5 of 6ICLR 2026 · 2 citations
- SOAR: Supervision from Observation for Agentic Reinforcement LearningAuthor 3 of 7ACL 2026 · 1 citation
- CR: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse AutoencodersAuthor 2 of 5ICML 2026
- Influence-based Online Experience Selection for Effective RLHFAuthor 3 of 6ACL 2026
- PanoramaRAG: Enabling Consistent Global Topic Awareness in Graph-Based RAGAuthor 5 of 5ACL Findings 2026
- RATT: A Thought Structure for Coherent and Correct LLM ReasoningAuthor 2 of 6AAAI 2025 · 51 citations
- Controlling Large Language Models Through Concept Activation VectorsAuthor 2 of 5AAAI 2025 · 26 citations
- Entropy-based Exploration Conduction for Multi-step ReasoningAuthor 2 of 6ACL Findings 2025 · 5 citations
- Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work GenerationAuthor 3 of 4ACL Findings 2025 · 2 citations
- Internal Value Alignment in Large Language Models through Controlled Value Vector ActivationAuthor 3 of 7ACL 2025
- Optimal Transport-Based Token Weighting scheme for Enhanced Preference OptimizationAuthor 4 of 5ACL 2025
- Think Then React: Towards Unconstrained Action-to-Reaction Motion GenerationAuthor 5 of 6ICLR 2025
- Uncovering Safety Risks of Large Language Models through Concept Activation VectorAuthor 4 of 4NeurIPS 2024 · 83 citations
- Persuading across Diverse Domains: a Dataset and Persuasion Large Language ModelAuthor 4 of 6ACL 2024 · 9 citations
- See or Guess: Counterfactually Regularized Image CaptioningAuthor 4 of 6ACM MM 2024 · 7 citations
- Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language ModelsAuthor 2 of 9ACL 2024 · 3 citations
- Evaluating Readability and Faithfulness of Concept-based ExplanationsAuthor 8 of 8EMNLP 2024 · 1 citation
- PENS: A Dataset and Generic Framework for Personalized News Headline GenerationAuthor 2 of 7ACL 2021
