Hang Su, Monica Sunkara, Saab Mansour, Igor Shalyminov, Jason Cai
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality typically involve LLM selfimprovement / self-reflection that incorporate feedback from models themselves. Despite their effectiveness, these methods are hindered by their high computational cost and lack of scalability. In this work, we propose CERET, a method for refining text generations by considering semantic stability, entailment and intersample uncertainty measures. Experimental results show that CERET outperforms Selfconsistency and Self-rerank baselines consistently under various task setups, by 1.6% in Rouge-1 for abstractive summarization and 3.5% in hit rate for question answering. Compared to LLM Self-rerank method, our approach only requires 9.4% of its latency and is more cost-effective. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.05588")
get_code_for_paper("2406.05588")
have("2406.05588")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.05588.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.05588)
Connect an agent — have() is free.