6 papers · 1 filter
BaseCal: Unsupervised Confidence Calibration via Base Model Signals
Hexiang Tan, Wanli Yang, Junwei Zhang +7
Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed post-trained LLMs (PoLLMs) typically compromise this trust with severe overconfidence. In con…
Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
Wanli Yang, Hongyu Zang, Junwei Zhang +5
Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We stu…
Fine-tuning Done Right in Model Editing
Wanli Yang, Rui Tang, Hongyu Zang +6
Fine-tuning, a foundational method for adapting large language models, has long been considered ineffective for model editing. Here, we challenge this belief, arguing that the repo…
The Mirage of Model Editing: Revisiting Evaluation in the Wild
Wanli Yang, Fei Sun, Jiajun Tan +5
Despite near-perfect results reported in the literature, the effectiveness of model editing in real-world applications remains unclear. To bridge this gap, we introduce QAEdit, a n…
Understanding the Collapse of LLMs in Model Editing
Wanli Yang, Fei Sun, Jiajun Tan +4
Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse. A…
Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
Hexiang Tan, Fei Sun, Wanli Yang +3
While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts genera…