Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better (2024 · 16 citations)
The paper tackles detection of machine-generated text (MGT) and addresses three weaknesses of DetectGPT. Its random perturbations can inject noise. It reduces perturbation to a single probability-difference score. Its threshold-based logit regression generalizes poorly and fails on single or small-batch inputs. The…
Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization (2025 · 7 citations)
Large language models can reproduce training passages word for word, which creates privacy and copyright risks.
Confidence Should Be Calibrated More Than One Turn Deep (2026 · 3 citations)
Research on LLM confidence calibration has mostly looked at single-turn question answering. Real deployments, however, involve dialogues where users push back. The authors define multi-turn calibration : confidence must match accuracy at every turn, given the conversation history. They introduce ECE@T , which…

Co-authors here

6 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 21 times (of the 149,439 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated 31 October 2026