REVIEW 5 cited by
ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary
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
The literature review is an indispensable step in the research process. It provides the benefit of comprehending the research problem and understanding the current research situation while conducting a comparative analysis of prior works. However, literature summary is challenging and time consuming. The previous LLM-based studies on literature review mainly focused on the complete process, including literature retrieval, screening, and summarization. However, for the summarization step, simple CoT method often lacks the ability to provide extensive comparative summary. In this work, we firstly focus on the independent literature summarization step and introduce ChatCite, an LLM agent with human workflow guidance for comparative literature summary. This agent, by mimicking the human workflow, first extracts key elements from relevant literature and then generates summaries using a Reflective Incremental Mechanism. In order to better evaluate the quality of the generated summaries, we devised a LLM-based automatic evaluation metric, G-Score, in refer to the human evaluation criteria. The ChatCite agent outperformed other models in various dimensions in the experiments. The literature summaries generated by ChatCite can also be directly used for drafting literature reviews.
Forward citations
Cited by 5 Pith papers
-
MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
MemGuide retrieves and filters past dialogue memories by intent and missing slots, and on its new synthetic benchmark MS-TOD it improves task success by 11 points and shortens dialogues by 2.84 turns.
-
Completing A Systematic Review in Hours instead of Months with Interactive AI Agents
An interactive, multi-agent LLM-based system with visual oversight lets one clinician complete a systematic review in about 1.5 hours while reaching about 80% of human-written review quality.
-
ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communities
ComViewer adds zoomable topic circles, support-type filters, and LLM-based note-taking and questioning to online mental health communities, and a within-subjects study shows more informational support and engagement v...
-
AIGS: Generating Science from AI-Powered Automated Falsification
Baby-AIGS is a multi-agent system that automates research through explicit falsification, outperforming its baseline on three ML tasks but lagging human experts.
-
Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms
ChatCite is presented as a new LLM method for comparative literature summarization, but the paper's evidence is under-specified and the method name duplicates a cited prior work.
Discussion (0). Continue with ORCID to comment.