Pith. sign in

Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (PLM), the large-scale language model (LLM) is utilized as a zero-shot re-ranker with excellent results. While LLM is highly dependent on the prompts, the impact and the optimization of the prompts for the zero-shot re-ranker are not explored yet. Along with highlighting the impact of optimization on the zero-shot re-ranker, we propose a novel discrete prompt optimization method, Constrained Prompt generation (Co-Prompt), with the metric estimating the optimum for re-ranking. Co-Prompt guides the generated texts from PLM toward optimal prompts based on the metric without parameter update. The experimental results demonstrate that Co-Prompt leads to outstanding re-ranking performance against the baselines. Also, Co-Prompt generates more interpretable prompts for humans against other prompt optimization methods.

citation-role summary

background 1

citation-polarity summary

fields

cs.IR 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • PaSa: An LLM Agent for Comprehensive Academic Paper Search cs.IR · 2025-01-17 · conditional · none · ref 27 · internal anchor

    PaSa, a two-agent LLM system trained with session-level RL, reports substantially higher recall than existing academic search baselines on complex paper-finding queries.