kaistAI / knowledge-reasoningLinks
[EMNLP 2024] Official implementation of "Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization"
โ21Updated 6 months ago
Alternatives and similar repositories for knowledge-reasoning
Users that are interested in knowledge-reasoning are comparing it to the libraries listed below
Sorting:
- [๐๐๐๐๐ ๐ ๐ข๐ง๐๐ข๐ง๐ ๐ฌ ๐๐๐๐ & ๐๐๐ ๐๐๐๐ ๐๐๐๐๐ ๐๐ซ๐๐ฅ] ๐๐ฏ๐ฉ๐ข๐ฏ๐ค๐ช๐ฏ๐จ ๐๐ข๐ต๐ฉ๐ฆ๐ฎ๐ข๐ต๐ช๐ค๐ข๐ญ ๐๐ฆ๐ข๐ด๐ฐ๐ฏ๐ช๐ฏโฆโ51Updated last year
- โ27Updated 2 years ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignmentโ16Updated 6 months ago
- Official Code Repository for the paper "Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-intensive Tasksโฆโ38Updated 7 months ago
- Methods and evaluation for aligning language models temporallyโ29Updated last year
- AbstainQA, ACL 2024โ26Updated 8 months ago
- SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433โ26Updated 6 months ago
- [ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Modelsโ22Updated last year
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our focโฆโ32Updated last year
- [EMNLP 2023] Once Upon a *Time* in *Graph*: Relative-Time Pretraining for Complex Temporal Reasoningโ17Updated last year
- Repository for "Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators"โ12Updated 3 months ago
- Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"โ32Updated last year
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"โ69Updated last year
- This is a unified platform for implementing and evaluating test-time reasoning mechanisms in Large Language Models (LLMs).โ19Updated 5 months ago
- Official code and dataset for our NAACL 2024 paper: DialogCC: An Automated Pipeline for Creating High-Quality Multi-modal Dialogue Dataseโฆโ13Updated last year
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."โ42Updated 8 months ago
- Self-Supervised Alignment with Mutual Informationโ19Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineeringโ60Updated 7 months ago
- Restore safety in fine-tuned language models through task arithmeticโ28Updated last year
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"โ38Updated last year
- โ29Updated last year
- "FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context Learning" (ACL 2023)โ14Updated last year
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"โ40Updated 9 months ago
- โ22Updated 10 months ago
- โ41Updated last year
- Unofficial Implementation of Chain-of-Thought Reasoning Without Promptingโ32Updated last year
- [ICLR 2025] ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domainsโ16Updated 3 months ago
- Adding new tasks to T0 without catastrophic forgettingโ33Updated 2 years ago
- [NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"โ38Updated last year
- โ40Updated last year