Identifies the generative-discriminative gap in LLM hard negative synthesis for retrieval and proposes CausalNeg using CoT counterfactual perturbation plus query-view entropy maximization to generate more effective negatives.
ISBN 9781450380379
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A new offline protocol to profile recommender algorithms by stability in retaining past patterns and plasticity in adapting to changes upon retraining, with preliminary results on the GoodReads dataset.
LLM-generated synthetic hard negatives for training dense retrievers consistently underperform corpus-mined negatives from BM25 and cross-encoders across 10 BEIR datasets, with non-monotonic gains from scaling the generator from 4B to 30B parameters.
citing papers explorer
-
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Identifies the generative-discriminative gap in LLM hard negative synthesis for retrieval and proposes CausalNeg using CoT counterfactual perturbation plus query-view entropy maximization to generate more effective negatives.
-
Measuring the stability and plasticity of recommender systems
A new offline protocol to profile recommender algorithms by stability in retaining past patterns and plasticity in adapting to changes upon retraining, with preliminary results on the GoodReads dataset.
-
Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
LLM-generated synthetic hard negatives for training dense retrievers consistently underperform corpus-mined negatives from BM25 and cross-encoders across 10 BEIR datasets, with non-monotonic gains from scaling the generator from 4B to 30B parameters.