https://github.com/pixeli99/a-cfg
공식 코드Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
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/pku-yuangroup/machine-mindset
공식 코드Machine Mindset: An MBTI Exploration of Large Language Models
https://github.com/pliang279/LM_bias
공식 코드Towards Understanding and Mitigating Social Biases in Language Models
https://github.com/pluslabnlp/amrfact
공식 코드AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation
https://github.com/pluslabnlp/cdm
공식 코드Open-Domain Text Evaluation via Contrastive Distribution Methods
https://github.com/pluslabnlp/clipscore-bias
공식 코드Gender Biases in Automatic Evaluation Metrics for Image Captioning
https://github.com/pluslabnlp/degree
공식 코드DEGREE: A Data-Efficient Generation-Based Event Extraction Model
https://github.com/pluslabnlp/sonnet-gen
공식 코드Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features
https://github.com/pluslabnlp/x-gear
공식 코드Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction
https://github.com/poloclub/llm-attribution
공식 코드LLM Attributor: Interactive Visual Attribution for LLM Generation
https://github.com/poloclub/llm-attributor
공식 코드LLM Attributor: Interactive Visual Attribution for LLM Generation
https://github.com/poloclub/llm-self-defense
공식 코드LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
https://github.com/poloclub/mememo
공식 코드MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation
https://github.com/ppartha03/Dialogue-Probe-Tasks-Public
공식 코드https://github.com/ppartha03/Semantic-Loss-Dialogue-Generation
공식 코드A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
https://github.com/prakashkagitha/llm-pddl-gen
공식 코드https://github.com/prakharguptaz/EDGE-exemplars
공식 코드https://github.com/prakharguptaz/Instructdial
공식 코드InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
https://github.com/pranjalchitale/in-context-mt-analysis
공식 코드An Empirical Study of In-context Learning in LLMs for Machine Translation
https://github.com/prasanns/eel-reranking
공식 코드https://github.com/prateek-kacker/ABB-BERT
공식 코드ABB-BERT: A BERT model for disambiguating abbreviations and contractions
https://github.com/priberam/cera-summ
공식 코드Supervising the Centroid Baseline for Extractive Multi-Document Summarization
https://github.com/priberam/s2tsumm
공식 코드https://github.com/princeton-nlp/Collie
공식 코드COLLIE: Systematic Construction of Constrained Text Generation Tasks
https://github.com/princeton-nlp/impersona
공식 코드https://github.com/probcomp/hfppl
공식 코드Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
https://github.com/probcomp/llamppl
공식 코드Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
https://github.com/probe2/kg_text
공식 코드Evaluating and Improving Graph to Text Generation with Large Language Models
https://github.com/psoulos/dtm
공식 코드Differentiable Tree Operations Promote Compositional Generalization
https://github.com/pspdada/SENTINEL
공식 코드Mitigating Object Hallucinations via Sentence-Level Early Intervention
https://github.com/pvop/clh3g
공식 코드Contrastive Learning enhanced Author-Style Headline Generation
https://github.com/pytorch/fairseq
공식 코드https://github.com/qhjqhj00/webbrain
공식 코드https://github.com/qianyue-wang/dome
공식 코드Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement
https://github.com/qibinc/KOBE
공식 코드Towards Knowledge-Based Personalized Product Description Generation in E-commerce
https://github.com/qijimrc/robustoie
공식 코드Syntactically Robust Training on Partially-Observed Data for Open Information Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.