ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation (2023 · 136 citations)
Most toxicity detectors are trained on social media text. Users of LLM chatbots behave differently: they phrase harmful intent as questions or instructions, and they sometimes use "jailbreaking" prompts that look benign but aim to make the model bypass its policies. To study this gap, the authors built ToxicChat, the…
Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning (2024 · 57 citations)
The paper asks whether large language models can improve their reasoning by learning from their own errors, rather than only imitating gold-standard Chain-of-Thought (CoT) rationales.
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026)
Industrial customer-service agents are usually built as chains of separate modules: routing, retrieval, planning, execution, response writing and review, as in the PEER pipeline.

Co-authors here

8 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 130 times (of the 149,439 papers whose bibliographies we read); 35 citing papers with a page here →.

Updated 1 November 2026