Pith. sign in

REVIEW 11 cited by

Recipes for building an open-domain chatbot

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2004.13637 v2 pith:RLZ4WHZO submitted 2020-04-28 cs.CL cs.AI

Stephen Roller , Emily Dinan , Naman Goyal , Da Ju , Mary Williamson , Yinhan Liu , Jing Xu , Myle Ott
show 4 more authors
Kurt Shuster Eric M. Smith Y-Lan Boureau Jason Weston
This is my paper · ORCID
classification cs.CLcs.AI
keywords modelsbuildingchatbotdatanumberopen-domainrecipesskills
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that large scale models can learn these skills when given appropriate training data and choice of generation strategy. We build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make our models and code publicly available. Human evaluations show our best models are superior to existing approaches in multi-turn dialogue in terms of engagingness and humanness measurements. We then discuss the limitations of this work by analyzing failure cases of our models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On the Fitness Landscape in the $NK$ Model

    math.PR 2025-08 unverdicted novelty 7.0 of 10

    For the NK fitness landscape with K/N tending to alpha, exact limits for free energy and maximum fitness are identified, together with the geometry of near-fittest peaks.

  2. LobRA: Multi-tenant Fine-tuning over Heterogeneous Data

    cs.DC 2025-09 accept novelty 6.0 of 10

    LobRA reduces GPU seconds for multi-tenant LoRA fine-tuning by 45.03%-60.67% through heterogeneous FT replicas and per-step workload-balanced dispatching.

  3. semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage

    cs.CL 2025-04 conditional novelty 6.0 of 10

    semi-PD is an LLM serving system that disaggregates prefill and decode compute at the streaming multiprocessor level over a unified GPU memory pool, and reports 1.27-2.58x lower average latency and 1.55-1.72x higher S...

  4. Precise Length Control in Large Language Models

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Adding a reversed, scaled sinusoidal positional encoding to a fine-tuned decoder-only LLM lets it end responses within about three tokens of a requested length.

  5. Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recovery

    cs.HC 2024-12 conditional novelty 6.0 of 10

    A 10-day field study found that an LLM chatbot supported eating disorder recovery through private storytelling, yet also produced unnoticed harmful responses such as praising weight loss and restriction.

  6. Benchmarking LLMs for Mimicking Child-Caregiver Language in Interaction

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Modern LLMs mimic child and caregiver speech at the word and sentence level but exaggerate conversational alignment and show less diversity than real parent-child dialogue.

  7. MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs

    cs.AI 2025-07 conditional novelty 5.0 of 10

    MMGraphRAG links scene-graph entities from images to text knowledge graph entities via SpecLink, and reports accuracy gains over naive RAG and GraphRAG on multimodal document QA.

  8. Automated Feedback Loops to Protect Text Simplification with Generative AI from Information Loss

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Adding all missing named entities back into simplified biomedical text yields the highest cosine similarity and ROUGE-1 to the original among five insertion strategies, but the evaluation is partly circular and lacks ...

  9. Mind the Language Gap: Automated and Augmented Evaluation of Bias in LLMs for High- and Low-Resource Languages

    cs.CL 2025-04 conditional novelty 5.0 of 10

    LLM-based translation and paraphrasing can effectively augment multilingual bias testing, and low-resource languages tend to show worse bias-detection scores than high-resource ones.

  10. Large Language Model guided Deep Reinforcement Learning for Decision Making in Autonomous Driving

    cs.RO 2024-12 conditional novelty 5.0 of 10

    An LLM-guided reinforcement learning framework with a JS-divergence policy constraint and intermittent safety interventions reaches 90% lane-change task success in highway-env, outperforming SAC-based baselines.

  11. Real-Time Textless Dialogue Generation

    cs.CL 2025-01 conditional novelty 4.0 of 10

    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.

Pith tools