Alternatives and similar repositories for rlhf-length-biases:

Users that are interested in rlhf-length-biases are comparing it to the libraries listed below

• kaistAI / InstructIR
  IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…
  ☆31Updated 10 months ago
• yuzhaouoe / pretraining-data-packing
  [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training
  ☆20Updated 7 months ago
• qtli / GSM-Plus
  GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.
  ☆59Updated 9 months ago
• GAIR-NLP / MetaCritique
  Evaluate the Quality of Critique
  ☆34Updated 10 months ago
• neulab / data-agora
  [arXiv preprint] Official Repository for "Evaluating Language Models as Synthetic Data Generators"
  ☆34Updated 4 months ago
• ekinakyurek / influence
  Code for "Tracing Knowledge in Language Models Back to the Training Data"
  ☆37Updated 2 years ago
• kaistAI / Janus
  [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
  ☆45Updated 4 months ago
• violet-zct / swarm-distillation-zero-shot
  ☆22Updated 2 years ago
• kaistAI / factual-knowledge-acquisition
  ☆17Updated 6 months ago
• hbin0701 / Self-Explore
  [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…
  ☆49Updated 11 months ago
• r-three / RAD
  Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
  ☆42Updated last year
• GAIR-NLP / benbench
  Benchmarking Benchmark Leakage in Large Language Models
  ☆51Updated 10 months ago
• swj0419 / in-context-pretraining
  ☆48Updated last year
• gmftbyGMFTBY / Rep-Dropout
  [NeurIPS 2023] Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective
  ☆30Updated last year
• kernelmachine / demix
  DEMix Layers for Modular Language Modeling
  ☆53Updated 3 years ago
• nathanhu0 / CaMeLS
  Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.
  ☆25Updated last year
• RLHFlow / Directional-Preference-Alignment
  Directional Preference Alignment
  ☆56Updated 6 months ago
• syncdoth / Chain-of-Hindsight-PyTorch
  Unofficial implementation of Chain of Hindsight (https://arxiv.org/abs/2302.02676) using pytorch and huggingface Trainers.
  ☆11Updated 2 years ago
• ernie-research / Tool-Augmented-Reward-Model
  [ICLR'24 spotlight] Tool-Augmented Reward Modeling
  ☆47Updated 3 months ago
• ThomasScialom / T0_continual_learning
  Adding new tasks to T0 without catastrophic forgetting
  ☆33Updated 2 years ago
• petezh / OpenD5
  Tasks for describing differences between text distributions.
  ☆16Updated 8 months ago
• Nanami18 / Snowballed_Hallucination
  ☆44Updated 7 months ago
• wzhouad / context-faithful-llm
  Code and data for paper "Context-faithful Prompting for Large Language Models".
  ☆39Updated 2 years ago
• princeton-nlp / WhatICLLearns
  [ACL 2023 Findings] What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning
  ☆21Updated last year
• Re-Align / AlignTDS
  Analyzing LLM Alignment via Token distribution shift
  ☆16Updated last year
• SimengSun / ChapterBreak
  ☆11Updated 10 months ago
• SumilerGAO / SunGen
  ☆25Updated 2 years ago
• XiangLi1999 / AutoBencher
  ☆26Updated 9 months ago
• allenai / natural-instructions-v1
  Benchmarking Generalization to New Tasks from Natural Language Instructions
  ☆26Updated 3 years ago
• shadowkiller33 / Contrast-Instruction
  ☆19Updated last year