Pith. sign in

REVIEW 7 cited by

Rewarding Chatbots for Real-World Engagement with Millions of Users

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

arxiv 2303.06135 v2 pith:A7GRGEQX submitted 2023-03-10 cs.CL cs.AIcs.LG

Rewarding Chatbots for Real-World Engagement with Millions of Users

classification cs.CL cs.AIcs.LG
keywords chatbotsmodeluserengagementlanguagerewardusersapproach
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The emergence of pretrained large language models has led to the deployment of a range of social chatbots for chitchat. Although these chatbots demonstrate language ability and fluency, they are not guaranteed to be engaging and can struggle to retain users. This work investigates the development of social chatbots that prioritize user engagement to enhance retention, specifically examining the use of human feedback to efficiently develop highly engaging chatbots. The proposed approach uses automatic pseudo-labels collected from user interactions to train a reward model that can be used to reject low-scoring sample responses generated by the chatbot model at inference time. Intuitive evaluation metrics, such as mean conversation length (MCL), are introduced as proxies to measure the level of engagement of deployed chatbots. A/B testing on groups of 10,000 new daily chatbot users on the Chai Research platform shows that this approach increases the MCL by up to 70%, which translates to a more than 30% increase in user retention for a GPT-J 6B model. Future work aims to use the reward model to realise a data fly-wheel, where the latest user conversations can be used to alternately fine-tune the language model and the reward model.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

    cs.CL 2026-04 unverdicted novelty 7.0

    CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.

  2. Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

    cs.CL 2026-04 accept novelty 7.0

    Cross-modal agreement between chain-of-thought and program-of-thought reasoning enables self-consistency with only two LLM samples, reducing sampling cost by 9.3x while improving accuracy.

  3. Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

    cs.CL 2026-07 conditional novelty 6.0

    PALATE trains five per-user simulators and personalized rubrics from real chat histories, then evaluates 16 role-playing agents on free multi-turn conversations, finding user-dependent winners.

  4. Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

    cs.CL 2026-07 conditional novelty 6.0

    A role-playing benchmark that uses per-person simulated users and personalized rubrics to co-construct and score free multi-turn dialogues, showing fixed-history evaluation is history-biased and user-specific rankings...

  5. Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

    cs.LG 2025-08 conditional novelty 6.0

    GSR jointly trains LLMs to generate candidate solutions and refine a superior final answer from them, achieving state-of-the-art performance on five mathematical benchmarks while transferring across model scales.

  6. Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

    cs.LG 2024-07 unverdicted novelty 6.0

    Repeated sampling scales problem coverage log-linearly with sample count, improving SWE-bench Lite performance from 15.9% to 56% using 250 samples.

  7. Chain-of-Verification Reduces Hallucination in Large Language Models

    cs.CL 2023-09 unverdicted novelty 6.0

    Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.