Papers with Code 아카이브

Instruction Following

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 1
보존된 평가 기록: 4

Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/QwenLM/AutoIF

공식 코드

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

https://github.com/Red-Hat-AI-Innovation-Team/orthogonal-subspace-learning

공식 코드

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

https://github.com/SALT-NLP/LLaVAR

공식 코드

LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding

https://github.com/THU-KEG/WaterBench

공식 코드

WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models

https://github.com/THU-MIG/PrefixKV

공식 코드

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

https://github.com/Taskii-Lei/Ex3-NovelWriter

공식 코드

Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding

https://github.com/TingchenFu/ACL24-ExpertFusion

공식 코드

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction

https://github.com/U-Alberta/AMRS3

공식 코드

Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM

https://github.com/UKPLab/arxiv2024-IRCoder

공식 코드

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators

https://github.com/VARGPT-family/VARGPT

공식 코드

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

https://github.com/WYRipple/SOTOPIA-Omega

공식 코드

SOTOPIA-$Ω$: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents

https://github.com/WangRongsheng/Aurora

공식 코드

Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning

https://github.com/WisdomShell/RewardAnything

공식 코드

RewardAnything: Generalizable Principle-Following Reward Models

https://github.com/YJiangcm/BMC

공식 코드

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

https://github.com/YihanWang617/context_awareness

공식 코드

On the Loss of Context-awareness in General Instruction Fine-tuning

https://github.com/Zhoues/MineDreamer

공식 코드

MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control

https://github.com/aashish2000/cordial

공식 코드

CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?

https://github.com/abzb1/alingment_calibration

공식 코드

Does Alignment Tuning Really Break LLMs' Internal Confidence?

https://github.com/acmislab/pediabench

공식 코드

PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models

https://github.com/adaxry/post-instruction

공식 코드

Instruction Position Matters in Sequence Generation with Large Language Models

https://github.com/adelaidehsu/rec

공식 코드

Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models

https://github.com/ai4bharat/fbi

공식 코드

Finding Blind Spots in Evaluator LLMs with Interpretable Checklists

https://github.com/aimagelab/LLaVA-MORE

공식 코드

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

https://github.com/airi-institute/igor

공식 코드

Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments

https://github.com/alibaba/graphtranslator

공식 코드

GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks

https://github.com/alibabaresearch/damo-convai

공식 코드

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization

https://github.com/allenai/href

공식 코드

HREF: Human Response-Guided Evaluation of Instruction Following in Language Models

https://github.com/allenai/natural-instructions

공식 코드

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

https://github.com/allenai/open-instruct

공식 코드

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

https://github.com/allenai/reward-bench

공식 코드

RewardBench: Evaluating Reward Models for Language Modeling

https://github.com/allenai/sciriff

공식 코드

SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature

https://github.com/allenxuuu/disco

공식 코드

DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control

https://github.com/alphadl/languageaware_tuning

공식 코드

Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning

https://github.com/amazon-science/alexa-arena

공식 코드

Alexa Arena: A User-Centric Interactive Platform for Embodied AI

https://github.com/amazon-science/setlexsem-challenge

공식 코드

SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models

https://github.com/andyrdt/refusal_direction

공식 코드

Refusal in Language Models Is Mediated by a Single Direction

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.