Papers with Code 아카이브
Text Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 25
- 평가표
- 155
- 보존된 평가 기록
- 54
Text Generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as "natural language generation" in the literature.
Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU.
Further readings:
<span style="color:grey; opacity: 0.6">( Image credit: Adversarial Ranking for Language Generation )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dvlab-research/prompt-highlighter
공식 코드Prompt Highlighter: Interactive Control for Multi-Modal LLMs
https://github.com/dwlmt/knowledgeable-stories
공식 코드https://github.com/e184633/semantic-answer-similarity
공식 코드https://github.com/eaglew/clbd
공식 코드SciMON: Scientific Inspiration Machines Optimized for Novelty
https://github.com/ebagdasa/adversarial_illusions
공식 코드https://github.com/ebagdasa/propaganda_as_a_service
공식 코드Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures
https://github.com/ecnuljzhang/brush-your-text
공식 코드Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model
https://github.com/edenbd/multimodalstory-demo
공식 코드FairyTailor: A Multimodal Generative Framework for Storytelling
https://github.com/edensaig/llm-contracts
공식 코드Incentivizing Quality Text Generation via Statistical Contracts
https://github.com/edillower/cyclenlg
공식 코드Faithful Low-Resource Data-to-Text Generation through Cycle Training
https://github.com/educationaltestingservice/concept-control-gen
공식 코드https://github.com/egojr/optagan
공식 코드https://github.com/ekaterinavoloshina/chronological_probing
공식 코드Is neural language acquisition similar to natural? A chronological probing study
https://github.com/elbria/xformal-fost-meta
공식 코드https://github.com/eleutherai/gpt-neox
공식 코드Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models
https://github.com/eleutherai/pythia
공식 코드Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System
https://github.com/eliorsulem/HSplit-corpus
공식 코드BLEU is Not Suitable for the Evaluation of Text Simplification
https://github.com/elisakreiss/concadia
공식 코드Concadia: Towards Image-Based Text Generation with a Purpose
https://github.com/elliottyan/understand-icl-from-repetition
공식 코드https://github.com/emalach/linearlm
공식 코드Auto-Regressive Next-Token Predictors are Universal Learners
https://github.com/emanuelevivoli/CoMix
공식 코드CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
https://github.com/emnlp-2024-critics/collective-critics-for-creative-story-generation
공식 코드https://github.com/emorynlp/seq2seq-corenlp
공식 코드https://github.com/epfl-dlab/sketchgcd
공식 코드Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
https://github.com/epfl-dlab/understanding-decoding
공식 코드https://github.com/epfl-nlp/kogito
공식 코드https://github.com/epfllm/meditron
공식 코드MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
https://github.com/ephemeral182/empirical-study-of-gpt-4o-image-gen
공식 코드https://github.com/eranhirs/sentence_union_generation
공식 코드Revisiting Sentence Union Generation as a Testbed for Text Consolidation
https://github.com/eric-ai-lab/minigpt-5
공식 코드MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens
https://github.com/erichen0615/controldag
공식 코드https://github.com/ernestgong/data2text-three-dimensions
공식 코드https://github.com/ernie-research/ma-rlhf
공식 코드MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
https://github.com/espnet/espnet
공식 코드https://github.com/eth-sri/chatprotect
공식 코드Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.