Response Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 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

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

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 370 papers with code (914 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.

• Language Models are Unsupervised Multitask Learners
  14 Feb 2019 21 repositories listed
  Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
• A Diversity-Promoting Objective Function for Neural Conversation Models
  11 Oct 2015 14 repositories listed Syntology ran 2 of 13 samples · 11 unverified
  Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.
• Unified Language Model Pre-training for Natural Language Understanding and Generation
  8 May 2019 9 repositories listed
  This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
• A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
  19 May 2016 9 repositories listed
  Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue.
• NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist
  15 May 2023 7 repositories listed
  Our proposed framework provides access: (i) for verifying whether automatic metrics are faithful to human preference, regardless of their correlation level to human; and (ii) for inspecting the strengths and limitations…
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
  7 May 2019 7 repositories listed
  Pre-training and fine-tuning, e.
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
  17 Oct 2023 6 repositories listed Syntology ran 8 of 14 samples · 6 unverified · 3 pointer-only (licence)
  Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens.
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
  1 Nov 2019 6 repositories listed Syntology ran 2 of 12 samples · 10 unverified · 12 pointer-only (licence)
  We present a large, tunable neural conversational response generation model, DialoGPT (dialogue generative pre-trained transformer).
• MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
  29 Sep 2018 5 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available.
• ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
  17 Jun 2024 4 repositories listed Syntology ran 20 of 30 samples · 10 unverified · 15 pointer-only (licence)
  Iterative self-improvement, a concept extending beyond personal growth, has found powerful applications in machine learning, particularly in transforming weak models into strong ones.
• Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset
  12 Sep 2019 4 repositories listed
  In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains.
• Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
  2 Jun 2016 4 repositories listed
  We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level…
• Self-Refine: Iterative Refinement with Self-Feedback
  30 Mar 2023 3 repositories listed
  Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
• PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
  30 Jun 2020 3 repositories listed
  To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning.
• PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
  17 Oct 2019 3 repositories listed
  Pre-training models have been proved effective for a wide range of natural language processing tasks.
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
  11 Sep 2019 3 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems.
• Response Generation by Context-aware Prototype Editing
  19 Jun 2018 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses.
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
  31 May 2018 3 repositories listed
  Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling.
• Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
  29 Jun 2017 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  However, previous work in dialogue response generation has shown that these metrics do not correlate strongly with human judgment in the non task-oriented dialogue setting.
• Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking
  14 Mar 2025 2 repositories listed
  In response, we show evaluations of existing RAG methods which account for both context relevance and answer quality.
• Survey on Abstractive Text Summarization: Dataset, Models, and Metrics
  22 Dec 2024 2 repositories listed
  This survey examines the state of the art in text summarization models, with a specific focus on the abstractive summarization approach.
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
  11 Oct 2024 2 repositories listed
  Reinforcement Learning (RL) plays a crucial role in aligning large language models (LLMs) with human preferences and improving their ability to perform complex tasks.
• Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models
  13 Jun 2024 2 repositories listed
  Subsequent analyses of these findings unveil insights into the effectiveness of various types of commonsense in generating responses and the particular response traits enhanced through explicit reasoning for commonsense…
• Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
  11 Oct 2023 2 repositories listed Syntology ran 3 of 6 samples · 3 unverified · 6 pointer-only (licence)
  In response to these challenges, we present an iterative search and reasoning framework, which consists of a textual encoder, a visual encoder, and a generator.
• Compressing Context to Enhance Inference Efficiency of Large Language Models
  9 Oct 2023 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact.
• Guiding Instruction-based Image Editing via Multimodal Large Language Models
  29 Sep 2023 2 repositories listed Syntology ran 3 of 6 samples · 3 unverified · 6 pointer-only (licence)
  Extensive experimental results demonstrate that expressive instructions are crucial to instruction-based image editing, and our MGIE can lead to a notable improvement in automatic metrics and human evaluation while…
• Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking
  26 Jul 2023 2 repositories listed
  Here we develop a novel few-shot overgenerate-and-rank approach that achieves the controlled generation of DAs.
• Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System
  4 May 2023 2 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  As results of the experiment, our method shows competitive performance on the MultiWOZ benchmark compared to the existing end-to-end models.
• Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
  20 Feb 2023 2 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied.
• Towards a Unified Multi-Dimensional Evaluator for Text Generation
  13 Oct 2022 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.

Syntology lines on 14 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.