Pith. sign in

REVIEW 1 cited by

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning

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 2402.14963 v2 pith:QBAHEQBF submitted 2024-02-22 cs.CL cs.AI

classification cs.CLcs.AI
keywords llmsmirrorreasoningknowledge-richmultiple-perspectiveself-reflectionaccessgenerated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources. In addition to the inefficiency of LLMs in self-assessment, we also observe that LLMs struggle to revisit their predictions despite receiving explicit negative feedback. Therefore, We propose Mirror, a Multiple-perspective self-reflection method for knowledge-rich reasoning, to avoid getting stuck at a particular reflection iteration. Mirror enables LLMs to reflect from multiple-perspective clues, achieved through a heuristic interaction between a Navigator and a Reasoner. It guides agents toward diverse yet plausibly reliable reasoning trajectory without access to ground truth by encouraging (1) diversity of directions generated by Navigator and (2) agreement among strategically induced perturbations in responses generated by the Reasoner. The experiments on five reasoning datasets demonstrate that Mirror's superiority over several contemporary self-reflection approaches. Additionally, the ablation study studies clearly indicate that our strategies alleviate the aforementioned challenges.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation

    cs.HC 2025-02 conditional novelty 6.0 of 10

    A new reflection-based AI method makes LLM-generated virtual students predict real students' future quiz performance better than deep learning knowledge-tracing baselines.

Pith tools