REVIEW 5 cited by
Retrieve and Refine: Improved Sequence Generation Models For Dialogue
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are restricted to the given retrieval set leading to erroneous replies that cannot be tuned to the specific context. In this work we develop a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it -- the final sequence generator treating the retrieval as additional context. We show on the recent CONVAI2 challenge task our approach produces responses superior to both standard retrieval and generation models in human evaluations.
Forward citations
Cited by 5 Pith papers
-
Zero-Shot Prompting Approaches for LLM-based Graphical User Interface Generation
A self-critique prompting loop outperformed retrieval-augmented and decomposed prompting for zero-shot generation of high-fidelity GUI prototypes, based on over 3,000 crowdworker ratings.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks
A decoder that hierarchically copies words from both conversation history and speaker facts produces more appropriate and more diverse grounded responses on the ConvAI2 benchmark.
-
Getting To Know You: User Attribute Extraction from Dialogues
A two-stage extractor, trained on NLI-generated distant supervision, pulls (subject, predicate, object) user attributes from chit-chat and beats retrieval and generation baselines in human evaluation.
-
Neural Text Generation with Unlikelihood Training
Training neural language models with an unlikelihood objective that penalizes repeated and frequent tokens reduces degenerate, repetitive text while preserving quality.
Discussion (0). Continue with ORCID to comment.