google-deepmind / latent-multi-hop-reasoning
[ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
☆65Updated last month
Alternatives and similar repositories for latent-multi-hop-reasoning
Users that are interested in latent-multi-hop-reasoning are comparing it to the libraries listed below
Sorting:
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 3 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆37Updated last week
- Lego for GRPO☆28Updated last month
- The first dense retrieval model that can be prompted like an LM☆72Updated last week
- ☆125Updated last month
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 4 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆98Updated 2 months ago
- Testing paligemma2 finetuning on reasoning dataset☆18Updated 4 months ago
- ☆16Updated 2 months ago
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆22Updated last month
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆90Updated 2 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆108Updated 2 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 7 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆42Updated last month
- ☆50Updated 5 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 3 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆92Updated 3 weeks ago
- ☆65Updated 2 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆33Updated this week
- accompanying material for sleep-time compute paper☆82Updated 2 weeks ago
- Simple repository for training small reasoning models☆27Updated 3 months ago
- ☆56Updated last week
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆173Updated 2 months ago
- ☆114Updated 2 months ago
- ☆18Updated this week
- ☆37Updated 3 months ago
- ☆27Updated 3 weeks ago
- Verifiers for LLM Reinforcement Learning☆50Updated last month
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 8 months ago