whyNLP / Conic10K

Related projects: ⓘ

• ernie-research / Tool-Augmented-Reward-Model
  [ICLR'24 spotlight] Tool-Augmented Reward Modeling
  ☆33Updated 6 months ago
• qtli / GSM-Plus
  GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.
  ☆38Updated 2 months ago
• RUCAIBox / BAMBOO
  ☆31Updated 5 months ago
• Shwai-He / MEO
  The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":
  ☆31Updated 5 months ago
• TianHongZXY / CoRe
  [ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models
  ☆33Updated 9 months ago
• SparkJiao / dpo-trajectory-reasoning
  Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
  ☆22Updated 5 months ago
• ChengpengLi1003 / DotaMath
  ☆23Updated 2 months ago
• Linear95 / DSP
  Domain-specific preference (DSP) data and customized RM fine-tuning.
  ☆24Updated 6 months ago
• GAIR-NLP / benbench
  Benchmarking Benchmark Leakage in Large Language Models
  ☆39Updated 4 months ago
• csitfun / LogiCoT
  the instructions and demonstrations for building a formal logical reasoning capable GLM
  ☆49Updated 2 weeks ago
• YuxiXie / SelfEval-Guided-Decoding
  ☆80Updated 9 months ago
• ChiyuSONG / dynamics-of-instruction-tuning
  ☆16Updated 6 months ago
• princeton-nlp / WhatICLLearns
  [ACL 2023 Findings] What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning
  ☆21Updated last year
• CriticBench / CriticBench
  [ACL 2024 Findings] CriticBench: Benchmarking LLMs for Critique-Correct Reasoning
  ☆20Updated 6 months ago
• ValueCompass / Alignment-Goal-Survey
  ☆25Updated 7 months ago
• GAIR-NLP / MetaCritique
  Evaluate the Quality of Critique
  ☆35Updated 3 months ago
• RLHFlow / Directional-Preference-Alignment
  Directional Preference Alignment
  ☆44Updated 3 months ago
• TianduoWang / DPO-ST
  [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
  ☆24Updated last month
• activatedgeek / calibration-tuning
  ☆30Updated last month
• OpenLMLab / ParallelTokenizer
  Use the tokenizer in parallel to achieve superior acceleration
  ☆15Updated 5 months ago
• wwxu21 / CUT
  Source code of "Reasons to Reject? Aligning Language Models with Judgments"
  ☆54Updated 6 months ago
• starrYYxuan / LeCo
  This the implementation of LeCo
  ☆16Updated 2 months ago
• xypan0 / G-DIG
  ☆10Updated 2 months ago
• chujiezheng / LLM-Extrapolation
  Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"
  ☆62Updated 3 months ago
• lqtrung1998 / mwp_cot_design
  ☆11Updated 11 months ago
• yale-nlp / refdpo
  ☆13Updated last month
• GAIR-NLP / ReasonEval
  Evaluating Mathematical Reasoning Beyond Accuracy
  ☆32Updated 5 months ago
• sail-sg / symbolic-instruction-tuning
  The official repository for the paper "From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning".
  ☆61Updated last year
• ars22 / scaling-LLM-math-synthetic-data
  Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"
  ☆22Updated 3 months ago
• chtmp223 / suri
  Code for Suri: Multi-constraint instruction following for long-form text generation
  ☆15Updated last week