Pith. sign in

REVIEW 2 cited by

SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation

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 2410.08356 v1 pith:NPTZ7Q5O submitted 2024-10-10 cs.HC

classification cs.HC
keywords behaviourinteractivesummactintentionsusernovelsummarisationactions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summarise low-level input actions into high-level intentions. SummAct first identifies sub-goals from user actions using a large language model and in-context learning. High-level intentions are then obtained by fine-tuning the model using a novel UI element attention to preserve detailed context information embedded within UI elements during summarisation. Through a series of evaluations, we demonstrate that SummAct significantly outperforms baselines across desktop and mobile interfaces as well as interactive tasks by up to 21.9%. We further show three exciting interactive applications benefited from SummAct: interactive behaviour forecasting, automatic behaviour synonym identification, and language-based behaviour retrieval.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users

    cs.AI 2025-02 conditional novelty 6.0 of 10

    A hierarchical auto-annotation pipeline plus episode-aware federated aggregation lets mobile GUI agents be trained on automatically labeled user trajectories at about 1% of human annotation cost.

  2. Bi-Fact: A Bidirectional Factorization-based Evaluation of Intent Extraction from UI Trajectories

    cs.AI 2025-02 conditional novelty 5.0 of 10

    Bi-Fact, a bidirectional fact-level LLM-based metric, reports higher agreement with human judgments than existing metrics when scoring intent extraction from GUI trajectories.

Pith tools