aryopg / decoreLinks
Official Implementation of "DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucination"
☆25Updated 10 months ago
Alternatives and similar repositories for decore
Users that are interested in decore are comparing it to the libraries listed below
Sorting:
- Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."☆16Updated 10 months ago
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆55Updated 8 months ago
- Codebase for Instruction Following without Instruction Tuning☆36Updated last year
- Exploration of automated dataset selection approaches at large scales.☆47Updated 7 months ago
- ☆17Updated 2 months ago
- ☆13Updated 8 months ago
- Long Context Extension and Generalization in LLMs☆61Updated last year
- ☆13Updated 3 months ago
- Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]☆35Updated last year
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆27Updated 7 months ago
- ☆18Updated 2 months ago
- ☆22Updated last year
- ☆35Updated last year
- Evaluate the Quality of Critique☆36Updated last year
- ☆50Updated 8 months ago
- Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"☆32Updated last year
- ☆19Updated 9 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆30Updated 2 months ago
- ☆15Updated last year
- [ACL'25] Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning☆20Updated 3 weeks ago
- ACL24☆10Updated last year
- Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"☆33Updated 3 months ago
- Codebase for Math Neurosurgery: Isolating LLMs' Math Reasoning Abilities Using Only Forward Passes☆19Updated 4 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year
- Benchmarking Benchmark Leakage in Large Language Models☆55Updated last year
- An evaluation suite for Retrieval-Augmented Generation (RAG).☆21Updated 5 months ago
- Source code of "Reasons to Reject? Aligning Language Models with Judgments"☆58Updated last year
- Lightweight Adapting for Black-Box Large Language Models☆23Updated last year
- ☆18Updated last year
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆102Updated last week