https://github.com/qcri/llmebench
공식 코드LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
Papers with Code 아카이브
In-Context Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/qingkaizeng/chain-of-layer
공식 코드https://github.com/qinyuanwu0710/zeroprompt_lke
공식 코드https://github.com/quest-lab-iisc/Learn-Unlearn-Relearn-Noise-SLMs
공식 코드Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?
https://github.com/quge2023/TA-SQL
공식 코드https://github.com/quinten-health-os/synth-data-gen-from-text
공식 코드A text-to-tabular approach to generate synthetic patient data using LLMs
https://github.com/r-three/t-few
공식 코드Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
https://github.com/raghav1606/summqa
공식 코드SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization
https://github.com/rajasekharmekala/query-rephrasing-subtask-cot
공식 코드EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning
https://github.com/ramituncc49er/atars
공식 코드Engineering Serendipity through Recommendations of Items with Atypical Aspects
https://github.com/raphaelmerx/llm-bilingual-examples
공식 코드Generating bilingual example sentences with large language models as lexicography assistants
https://github.com/rasahq/tod-in-context-learning
공식 코드https://github.com/redwyd/privacyjailbreak
공식 코드PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
https://github.com/relento/hypothesis_search
공식 코드https://github.com/rit-git/lm-know
공식 코드Measuring and Modifying Factual Knowledge in Large Language Models
https://github.com/rithiksachdev/PostASR-Correction-SLT2024
공식 코드Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction
https://github.com/rlawjdghek/promptdresser
공식 코드https://github.com/roeehendel/icl_task_vectors
공식 코드https://github.com/romainpkq/chatgpt4mt
공식 코드https://github.com/romainpkq/revisit_demon_selection_in_icl
공식 코드Revisiting Demonstration Selection Strategies in In-Context Learning
https://github.com/ronit-singhal/evidence-backed-fact-checking-using-rag-and-few-shot-in-context-learning-with-llms
공식 코드Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
https://github.com/rookiezxy/gbtl
공식 코드Learning to Poison Large Language Models for Downstream Manipulation
https://github.com/rorschach1989/transformer-for-gmm
공식 코드Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures
https://github.com/rpatrik96/llm-non-identifiability
공식 코드Position: Understanding LLMs Requires More Than Statistical Generalization
https://github.com/rucaibox/competitive-icl
공식 코드Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
https://github.com/rucaibox/mcts4zsicl
공식 코드DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning
https://github.com/rucaibox/quantizedempirical
공식 코드Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study
https://github.com/rucbm/icleval
공식 코드ICLEval: Evaluating In-Context Learning Ability of Large Language Models
https://github.com/ruili33/sec
공식 코드Are Human-generated Demonstrations Necessary for In-context Learning?
https://github.com/ruleGreen/AppBench
공식 코드AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
https://github.com/runnerup96/error-detection-in-text2sql
공식 코드Confidence Estimation for Error Detection in Text-to-SQL Systems
https://github.com/ruocwang/mixture-of-prompts
공식 코드One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
https://github.com/ruyue0001/decompose_icl_improvement
공식 코드https://github.com/rwkv/rwkv-lm
공식 코드https://github.com/ryuryukke/OUTFOX
공식 코드https://github.com/s-kumano/universally-robust-in-context-learner
공식 코드Adversarially Pretrained Transformers may be Universally Robust In-Context Learners
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.