{"id":19307376,"url":"https://github.com/artefactory/abstention-reranker","last_synced_at":"2026-03-14T08:35:23.436Z","repository":{"id":222106167,"uuid":"756235939","full_name":"artefactory/abstention-reranker","owner":"artefactory","description":null,"archived":false,"fork":false,"pushed_at":"2024-09-04T07:41:32.000Z","size":97,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-06T01:11:15.565Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/artefactory.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-12T08:58:49.000Z","updated_at":"2024-12-05T11:13:12.000Z","dependencies_parsed_at":"2024-02-23T09:26:09.116Z","dependency_job_id":"cbca51e9-a7d3-4312-83b4-0d9808166e85","html_url":"https://github.com/artefactory/abstention-reranker","commit_stats":null,"previous_names":["hgissbkh/abstention-reranker","artefactory/abstention-reranker"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fabstention-reranker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fabstention-reranker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fabstention-reranker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fabstention-reranker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/artefactory","download_url":"https://codeload.github.com/artefactory/abstention-reranker/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240409258,"owners_count":19796789,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-10T00:10:44.397Z","updated_at":"2025-12-25T08:51:15.146Z","avatar_url":"https://github.com/artefactory.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Abstention Reranker\n\nReference article: \"[Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism](https://arxiv.org/pdf/2402.12997.pdf)\" (accepted at TMLR, 09/2024).\n\n## Abstract\n\nNeural Information Retrieval (NIR) has significantly improved upon heuristic-based Information Retrieval (IR) systems. Yet, failures remain frequent, the models used often being unable to retrieve documents relevant to the user's query. We address this challenge by proposing a lightweight abstention mechanism tailored for real-world constraints, with particular emphasis placed on the reranking phase. We introduce a protocol for evaluating abstention strategies in black-box scenarios (typically encountered when relying on API services), demonstrating their efficacy, and propose a simple yet effective data-driven mechanism. We provide open-source code for experiment replication and abstention implementation, fostering wider adoption and application in diverse contexts.\n\n## Installation\n```python\npip install -r requirements.txt\n```\n\n## Computation of relevance scores\n\n```python \npython scripts/run_on_datasets.py --config-path \u003cpath to config YML\u003e\n```\n\n## Experiment replication\n\nSee [/notebooks/plots.ipynb](https://github.com/artefactory/abstention-reranker/blob/main/notebooks/plots.ipynb).\n\n## Usage examples\n\nSee [/notebooks/implem.ipynb](https://github.com/artefactory/abstention-reranker/blob/main/notebooks/implem.ipynb).\n\n## Reference\n\nIf you found our work useful, please consider citing:\n\n```\n@misc{gisserotboukhlef2024trustworthy,\n    title={Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism}, \n    author={Hippolyte Gisserot-Boukhlef and Manuel Faysse and Emmanuel Malherbe and Céline Hudelot and Pierre Colombo},\n    year={2024},\n    eprint={2402.12997},\n    archivePrefix={arXiv},\n    primaryClass={cs.IR}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fartefactory%2Fabstention-reranker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fartefactory%2Fabstention-reranker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fartefactory%2Fabstention-reranker/lists"}