https://github.com/orionw/followir
공식 코드mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval
Papers with Code 아카이브
Instruction Following
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/orionw/rank1
공식 코드Rank1: Test-Time Compute for Reranking in Information Retrieval
https://github.com/osu-nlp-group/eval-llm-trust
공식 코드https://github.com/osu-nlp-group/qa4re
공식 코드Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors
https://github.com/p-b-u/proxy_based_uncertainty
공식 코드Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
https://github.com/penfever/sos-bench
공식 코드Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
https://github.com/pjlab-songcomposer/songcomposer
공식 코드SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition
https://github.com/pku-alignment/align-anything
공식 코드Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
https://github.com/pku-rl/creative-agents
공식 코드Creative Agents: Empowering Agents with Imagination for Creative Tasks
https://github.com/pnnl/chemreasoner
공식 코드https://github.com/pppa2019/contexualdynamicmapping
공식 코드Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping
https://github.com/pppa2019/swie_overmiss_llm4mt
공식 코드Improving Translation Faithfulness of Large Language Models via Augmenting Instructions
https://github.com/princeton-nlp/cepe
공식 코드Long-Context Language Modeling with Parallel Context Encoding
https://github.com/princeton-nlp/llmbar
공식 코드Evaluating Large Language Models at Evaluating Instruction Following
https://github.com/princeton-nlp/simpo
공식 코드SimPO: Simple Preference Optimization with a Reference-Free Reward
https://github.com/princeton-pli/Instruct-SkillMix
공식 코드Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
https://github.com/probcomp/clips.jl
공식 코드Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning
https://github.com/prometheus-eval/prometheus-eval
공식 코드https://github.com/psunlpgroup/realmistake
공식 코드https://github.com/qinyiwei/infobench
공식 코드InFoBench: Evaluating Instruction Following Ability in Large Language Models
https://github.com/qizekun/ShapeLLM
공식 코드ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/qurrent-ai/res-q
공식 코드RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale
https://github.com/qwenlm/qwen-audio
공식 코드Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
https://github.com/qwenlm/qwen2-audio
공식 코드https://github.com/qwenlm/qwen2.5
공식 코드https://github.com/rahuln/instr-perf-pred
공식 코드Third-Party Language Model Performance Prediction from Instruction
https://github.com/raibows/learn-to-reason
공식 코드Democratizing Reasoning Ability: Tailored Learning from Large Language Model
https://github.com/rail-berkeley/soar
공식 코드Autonomous Improvement of Instruction Following Skills via Foundation Models
https://github.com/raojay7/commonit
공식 코드CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions
https://github.com/rayruibochen/self-filter
공식 코드https://github.com/reail-iitd/goalnet
공식 코드https://github.com/renshuhuai-andy/timechat
공식 코드TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
https://github.com/renzelou/awesome-instruction-learning
공식 코드Large Language Model Instruction Following: A Survey of Progresses and Challenges
https://github.com/renzelou/pick-rank
공식 코드https://github.com/rhyang2021/logu
공식 코드https://github.com/rhymes-ai/aria
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.