Conditional Text Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 32 papers with code (67 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation
  18 Nov 2022 2 repositories listed
  We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated…
• The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
  25 May 2022 2 repositories listed
  As a result, GST scales the amount of training data up to an order of magnitude that of VisDial (1.
• BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla
  23 May 2022 2 repositories listed
  This work presents BanglaNLG, a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language.
• Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation
  18 Apr 2021 2 repositories listed
  In this paper, we present a systematic analysis that studies whether current seq2seq models, especially pre-trained language models, are good enough for preserving important input concepts and to what extent explicitly…
• Unifying Vision-and-Language Tasks via Text Generation
  4 Feb 2021 2 repositories listed Syntology ran 2 of 12 samples · 10 unverified
  On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our…
• Pragmatically Informative Text Generation
  2 Apr 2019 2 repositories listed
  We improve the informativeness of models for conditional text generation using techniques from computational pragmatics.
• Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings
  24 Jun 2024 1 repository listed
  To address this gap, we have conducted a comprehensive survey of language models in the medical field and evaluated a subset of these for medical text classification and conditional text generation.
• TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings
  29 Feb 2024 1 repository listed
  This paper presents the Text Encoding Diffusion Model (TEncDM), a novel approach to diffusion modeling that operates in the space of pre-trained language model encodings.
• LOCOST: State-Space Models for Long Document Abstractive Summarization
  31 Jan 2024 1 repository listed
  State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies.
• Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models
  25 Jan 2024 1 repository listed
  We systematically study the effects of the phenomenon across NLI models for in- and out-of- domain settings.
• IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition
  19 Dec 2023 1 repository listed
  Nowadays, scene text recognition has attracted more and more attention due to its diverse applications.
• MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
  27 Nov 2023 1 repository listed Syntology ran 9 of 14 samples · 5 unverified
  Large language models (LLMs) can potentially democratize access to medical knowledge.
• Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
  25 Jul 2023 1 repository listed
  To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this…
• Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
  14 Jul 2023 1 repository listed
  Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks.
• Learning to Generate Better Than Your LLM
  20 Jun 2023 1 repository listed
  In particular, we extend RL algorithms to allow them to interact with a dynamic black-box guide LLM and propose RL with guided feedback (RLGF), a suite of RL algorithms for LLM fine-tuning.
• EEL: Efficiently Encoding Lattices for Reranking
  1 Jun 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Standard decoding approaches for conditional text generation tasks typically search for an output hypothesis with high model probability, but this may not yield the best hypothesis according to human judgments of…
• VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
  17 Apr 2023 1 repository listed
  Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner.
• AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling
  12 May 2022 1 repository listed
  Variational Auto-Encoder (VAE) has become the de-facto learning paradigm in achieving representation learning and generation for natural language at the same time.
• Regression Transformer: Concurrent sequence regression and generation for molecular language modeling
  1 Feb 2022 1 repository listed Syntology ran 0 of 8 samples · 8 unverified
  To that end, we propose the Regression Transformer (RT), a novel method that abstracts regression as a conditional sequence modeling problem.
• Exploring Conditional Text Generation for Aspect-Based Sentiment Analysis
  5 Oct 2021 1 repository listed
  Aspect-based sentiment analysis (ABSA) is an NLP task that entails processing user-generated reviews to determine (i) the target being evaluated, (ii) the aspect category to which it belongs, and (iii) the sentiment…
• WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
  20 Jul 2021 1 repository listed
  We present a new dataset of Wikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning.
• Is Everything in Order? A Simple Way to Order Sentences
  14 Apr 2021 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets.
• Data-to-text Generation by Splicing Together Nearest Neighbors
  20 Jan 2021 1 repository listed Syntology ran 9 of 10 samples · 1 unverified · 10 pointer-only (licence)
  We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs.
• Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
  14 Dec 2020 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In this work, we propose to mitigate the conditional text generation problem by contrasting positive pairs with negative pairs, such that the model is exposed to various valid or incorrect perturbations of the inputs,…
• On Long-Tailed Phenomena in Neural Machine Translation
  10 Oct 2020 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens, tackling which remains a major challenge.
• Plug and Play Autoencoders for Conditional Text Generation
  6 Oct 2020 1 repository listed
  Text autoencoders are commonly used for conditional generation tasks such as style transfer.
• ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation
  25 Aug 2020 1 repository listed
  We first test the effectiveness of our approach in a low-resource setting for Italian, evaluating the conditioning for both topic models and gold annotations.
• Token Manipulation Generative Adversarial Network for Text Generation
  6 May 2020 1 repository listed
  MaskGAN opens the query for the conditional language model by filling in the blanks between the given tokens.
• ToTTo: A Controlled Table-To-Text Generation Dataset
  29 Apr 2020 1 repository listed
  We present ToTTo, an open-domain English table-to-text dataset with over 120, 000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a…
• Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
  10 Nov 2019 1 repository listed
  Conditional Text Generation has drawn much attention as a topic of Natural Language Generation (NLG) which provides the possibility for humans to control the properties of generated contents.

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.