REVIEW 7 cited by
Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
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
Building socialbots that can have deep, engaging open-domain conversations with humans is one of the grand challenges of artificial intelligence (AI). To this end, bots need to be able to leverage world knowledge spanning several domains effectively when conversing with humans who have their own world knowledge. Existing knowledge-grounded conversation datasets are primarily stylized with explicit roles for conversation partners. These datasets also do not explore depth or breadth of topical coverage with transitions in conversations. We introduce Topical-Chat, a knowledge-grounded human-human conversation dataset where the underlying knowledge spans 8 broad topics and conversation partners don't have explicitly defined roles, to help further research in open-domain conversational AI. We also train several state-of-the-art encoder-decoder conversational models on Topical-Chat and perform automated and human evaluation for benchmarking.
Forward citations
Cited by 7 Pith papers
-
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
Inversion learning generates model-specific NLG evaluation prompts from a single human-annotated sample, and these prompts outperform hand-crafted and search-based prompts in correlation with human scores.
-
Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity
Multi-agent debate mostly underperforms simple chain-of-thought baselines when tested broadly, while randomly mixing different models into the debate reliably improves performance.
-
DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation
A dual-refinement method (DRE) that uses a contrastively trained small language model to guide and rescale an LLM's dialogue quality scores achieves higher correlation with human ratings than LLM-only baselines on thr...
-
Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning
Possibility Exploration Fine-Tuning (PEFT) conditions LLMs on a random possibility number and trains with unlikelihood to generate diverse, controllable responses without added latency, as shown on dialogue and story tasks.
-
Commonsense Generation and Evaluation for Dialogue Systems using Large Language Models
GPT-3.5 and GPT-4 can generate and evaluate turn-level commonsense dialogue expansions guided by ATOMIC relation definitions, with GPT-4 achieving the highest reranking accuracy.
-
Real-Time Textless Dialogue Generation
A streaming, textless dialogue model predicts turn-taking actions every 160 ms and generates speech units, improving naturalness over cascaded systems at the cost of lower semantic coherence.
-
MAPS: Modeling Co-Existing Subjective Perspectives and Shared Meaning in Multi-Agent Cognitive Dialogue
MAPS combines hand-coded domain weights, a GRU memory, and attention to let dialogue agents keep distinct subjective profiles while their hidden states are trained to move closer together.
Discussion (0). Continue with ORCID to comment.