CRAFT is a Pareto-front prompt optimizer that allocates scarce LLM validation calls to candidates near the current front using accuracy- and cost-oriented generators plus NSGA-II retention.
The Multilingual A mazon Reviews Corpus
6 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
6
Pith papers citing it
3
external citations · Crossref
representative citing papers
Prompt-based text embeddings can be truncated to a small fraction of their dimensions with little performance loss on classification and clustering, but retrieval and STS degrade faster; the difference tracks lower intrinsic dimensionality and isotropy.
A new Polish dataset and model evaluation show that fine-tuned Polish transformers detect dual-quality product reviews with precision close to GPT-4o.
ListConRanker combines listwise attention over passage embeddings with Circle Loss to set a new mAP average on the C-MTEB reranking benchmark.
JAPAGEN uses GPT-3.5 to produce Japanese pseudo-training data, letting compact BERT models beat few-shot fine-tuning on five of six tasks and beat zero-shot prompting on three of six.
citing papers explorer
-
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
CRAFT is a Pareto-front prompt optimizer that allocates scarce LLM validation calls to candidates near the current front using accuracy- and cost-oriented generators plus NSGA-II retention.
-
Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings
Prompt-based text embeddings can be truncated to a small fraction of their dimensions with little performance loss on classification and clustering, but retrieval and STS degrade faster; the difference tracks lower intrinsic dimensionality and isotropy.
-
Unveiling Dual Quality in Product Reviews: An NLP-Based Approach
A new Polish dataset and model evaluation show that fine-tuned Polish transformers detect dual-quality product reviews with precision close to GPT-4o.
-
ListConRanker: A Contrastive Text Reranker with Listwise Encoding
ListConRanker combines listwise attention over passage embeddings with Circle Loss to set a new mAP average on the C-MTEB reranking benchmark.
-
JAPAGEN: Efficient Few/Zero-shot Learning via Japanese Training Dataset Generation with LLM
JAPAGEN uses GPT-3.5 to produce Japanese pseudo-training data, letting compact BERT models beat few-shot fine-tuning on five of six tasks and beat zero-shot prompting on three of six.
- To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios