Papers with Code 아카이브
Long-Context Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 39
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/JasonForJoy/BRIEF
공식 코드BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression
https://github.com/NVlabs/GatedDeltaNet
공식 코드https://github.com/WUHU-G/RCC_Transformer
공식 코드Recurrent Context Compression: Efficiently Expanding the Context Window of LLM
https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2
공식 코드mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration
https://github.com/ZetangForward/L-CITEEVAL
공식 코드L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
https://github.com/Zhihan72/TCELongBench
공식 코드https://github.com/academycityl/gali
공식 코드A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
https://github.com/alinlab/homer
공식 코드Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
https://github.com/bigai-nlco/loogle
공식 코드LooGLE: Can Long-Context Language Models Understand Long Contexts?
https://github.com/cone-mt/benchmax
공식 코드BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
https://github.com/fla-org/flash-linear-attention
공식 코드MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
https://github.com/gatech-eic/longmamba
공식 코드LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement
https://github.com/google/curie
공식 코드CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning
https://github.com/hambaobao/marathon
공식 코드Marathon: A Race Through the Realm of Long Context with Large Language Models
https://github.com/hanzhizhang-ulrica/dam
공식 코드DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
https://github.com/hsiehjackson/ruler
공식 코드RULER: What's the Real Context Size of Your Long-Context Language Models?
https://github.com/jycha98/specextend
공식 코드SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences
https://github.com/lfy79001/s3eval
공식 코드S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models
https://github.com/lfy79001/sqleval
공식 코드S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models
https://github.com/librairesearch/scalar
공식 코드SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning
https://github.com/lm-sys/fastchat
공식 코드https://github.com/milkthink-lab/minilongbench
공식 코드MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models
https://github.com/moonshotai/kimi-vl
공식 코드https://github.com/mozerwang/loong
공식 코드Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
https://github.com/mungg/fables
공식 코드FABLES: Evaluating faithfulness and content selection in book-length summarization
https://github.com/naver-ai/prolip
공식 코드LongProLIP: A Probabilistic Vision-Language Model with Long Context Text
https://github.com/nightdessert/retrieval_head
공식 코드Retrieval Head Mechanistically Explains Long-Context Factuality
https://github.com/open-compass/ada-leval
공식 코드Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks
https://github.com/openai/evals
공식 코드https://github.com/p1nksnow/moice
공식 코드Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
https://github.com/pku-ml/longppl
공식 코드What is Wrong with Perplexity for Long-context Language Modeling?
https://github.com/pprp/acbench
공식 코드Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
https://github.com/princeton-pli/prulong
공식 코드Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?
https://github.com/quehry/hellobench
공식 코드HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
https://github.com/s1s-z/gateau
공식 코드GATEAU: Selecting Influential Samples for Long Context Alignment
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.