Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jiachen Li

Jiachen Li

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3

Frequent co-authors

Siyan Li1×
Zehao Wang1×
Kanok Boriboonsomsin1×
Matthew J. Barth1×
Guoyuan Wu1×
Minyang Hu1×

Research Timeline

2026
From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

The paper introduces Causal Editing (CODE), a new paradigm that improves knowledge updates in LLMs by grounding fact injection in causal narratives, drastically reducing self-refutation rates.

Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories

The paper introduces RedundancyBench, a new benchmark for detecting unnecessary steps in LLM agent trajectories, finding that this task is highly complex and difficult to solve.

Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support

This survey reviews how Large and Multi-modal Language Models (LLMs/MM-LLMs) are being applied to integrate diverse data sources for enhanced decision support in transportation systems management and operations.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 31, 2026

Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support

Siyan Li, Zehao Wang, Jiachen Li, Kanok Boriboonsomsin +2 more

This survey reviews how Large and Multi-modal Language Models (LLMs/MM-LLMs) are being applied to integrate diverse data sources for enhanced decision support in transportation systems management and…

View →
cs.AIRecentMay 28, 2026

Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories

Minyang Hu, Bo Yang, Zhinuo Zhou, Jiachen Liang +3 more

The paper introduces RedundancyBench, a new benchmark for detecting unnecessary steps in LLM agent trajectories, finding that this task is highly complex and difficult to solve.

View →
cs.AIRecentMay 27, 2026

From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

Shuaike Li, Kai Zhang, Xianquan Wang, Jiachen Liu +1 more

The paper introduces Causal Editing (CODE), a new paradigm that improves knowledge updates in LLMs by grounding fact injection in causal narratives, drastically reducing self-refutation rates.

View →