Large Language Models

Digital Socrates: Evaluating LLMs through Explanation Critiques ACL 2024 DiJiang: Efficient Large Language Models through Compact Kernelization ICML 2024 DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models ICML 2024 DINGO: Towards Diverse and Fine-Grained Instruction-Following Evaluation AAAI 2024 DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models NeurIPS 2024 Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs ACL 2024 Direct Multi-Turn Preference Optimization for Language Agents EMNLP 2024 Direct Preference Optimization for Suppressing Hallucinated Prior Exams in Radiology Report Generation MLHC 2024 Discovering Knowledge-Critical Subnetworks in Pretrained Language Models EMNLP 2024 Discovering Preference Optimization Algorithms with and for Large Language Models NeurIPS 2024 Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models NeurIPS 2024 Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution ICML 2024 Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations ACL 2024 Disentangling Length from Quality in Direct Preference Optimization ACL 2024 Disinformation Capabilities of Large Language Models ACL 2024 DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models NeurIPS 2024 Dissecting Fine-Tuning Unlearning in Large Language Models EMNLP 2024 DistiLLM: Towards Streamlined Distillation for Large Language Models ICML 2024 Distinguishing the Knowable from the Unknowable with Language Models ICML 2024 Distract Large Language Models for Automatic Jailbreak Attack EMNLP 2024 Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF ICLR 2024 Ditto: Quantization-aware Secure Inference of Transformers upon MPC ICML 2024 Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization EACL 2024 DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions EMNLP 2024 Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation NeurIPS 2024