Papers by Andrew Parry
Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that training examples improve zero-shot performance of supervised ranking models. |
| Approach: | They propose to augment supervised ranking models with pairs of queries and documents to improve their performance. |
| Outcome: | The proposed model outperforms the unsupervised models on in-domain and out-domain retrieval benchmarks. |
Exploiting Positional Bias for Query-Agnostic Generative Content in Search (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that neural ranking models outperform lexical models in text retrieval. |
| Approach: | They propose to exploit transformer attention mechanism to induce exploitable defects in search models through sensitivity to token position within a sequence. |
| Outcome: | The proposed model can generalise beyond a single query or topic without knowledge of topicality. |