27 citations · 29 across the 10 of their papers we have counts for
5 papers · 2 filters
Robust Failure, Conservative Repair: Textual Knowledge Distillation from Cross-Model Failures
Andrew Ren, Haokun Liu, Chenhao Tan
Failure-based textual knowledge distillation aims to discover gaps in a model's knowledge by examining its task errors. The distilled knowledge can be useful for the reasoning of b…
Emergent Misalignment Is Not Magical
Mingxuan Li, Qirun Dai, Heran Wang +1
Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM). EM poses a challenge for A…
VERITAS: Towards a General-Purpose Replication Tool for Scientific Research
Haokun Liu, Filbert Aurelian Tjiaranata, Chenhao Tan
AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published research has become both harder and…
Personalized Benchmarking: Evaluating LLMs by Individual Preferences
Cristina Garbacea, Heran Wang, Chenhao Tan
With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences has become an important chal…
Automatically Generating Hard Math Problems from Hypothesis-Driven Error Analysis
Jiayu Fu, Mourad Heddaya, Chenhao Tan
Numerous math benchmarks exist to evaluate LLMs' mathematical capabilities. However, most involve extensive manual effort and are difficult to scale. Consequently, they cannot keep…