One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning…
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Relianceby Sachin Goyal, Christina Baek,…
Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Modelsby…
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compressionby Mohammad Mozaffari, Amir…
FlatQuant: Flatness Matters for LLM Quantizationby Yuxuan Sun, Ruikang Liu, Haoli Bai, Han Bao, Kang…
Inference and Verbalization Functions During In-Context Learningby Junyi Tao, Xiaoyin Chen, Nelson F. LiuFirst submitted…
Nudging: Inference-time Alignment via Model Collaborationby Yu Fei, Yasaman Razeghi, Sameer SinghFirst submitted to arxiv…
SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selectionby Han Shen, Pin-Yu Chen, Payel Das,…
CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compressionby…
Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRAby Maharshi Gor,…