| To Code, or Not To Code? Exploring Impact of Code in Pre-training | Aug 20, 2024 | Code GenerationWorld Knowledge | —Unverified | 0 |
| CoDi: Conversational Distillation for Grounded Question Answering | Aug 20, 2024 | Question AnsweringWorld Knowledge | —Unverified | 0 |
| BLADE: Benchmarking Language Model Agents for Data-Driven Science | Aug 19, 2024 | BenchmarkingDecision Making | CodeCode Available | 1 |
| On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification | Aug 18, 2024 | ImputationMissing Labels | CodeCode Available | 0 |
| A Mechanistic Interpretation of Syllogistic Reasoning in Auto-Regressive Language Models | Aug 16, 2024 | Logical Reasoningvalid | —Unverified | 0 |
| MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty | Aug 13, 2024 | Mathematical ReasoningQuestion Answering | CodeCode Available | 0 |
| Prompt Tuning as User Inherent Profile Inference Machine | Aug 13, 2024 | QuantizationRecommendation Systems | —Unverified | 0 |
| LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description | Aug 9, 2024 | DiversityInstruction Following | CodeCode Available | 0 |
| Better Alignment with Instruction Back-and-Forth Translation | Aug 8, 2024 | DiversityTranslation | —Unverified | 0 |
| Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation | Aug 7, 2024 | Logical ReasoningRecommendation Systems | —Unverified | 0 |
