We lifted 11 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| sjj1017/citekit | canonical | 8 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| compute_str_em | Ran | sjj1017/citekit/citekit/utils/utils.py code served (permissive licence) · get_code("ece0969bd45a5478") |
| cut_and_make_as | Ran | sjj1017/citekit/methods/ALCE_interact.py code served (permissive licence) · get_code("7f4fb396d1f4c613") |
| get_cite | Ran | sjj1017/citekit/citekit/evaluator/evaluator.py code served (permissive licence) · get_code("1d50ff426c4bbbbd") |
| gtr_build_index | Ran | sjj1017/citekit/citekit/cite_modules/Retrieve.py code served (permissive licence) · get_code("e11e7457d509e77d") |
| merge_str_dicts | Ran | sjj1017/citekit/citekit/pipeline/pipeline.py code served (permissive licence) · get_code("1e09632cc01ef34a") |
| one_paragraph | Ran | sjj1017/citekit/citekit/utils/utils.py code served (permissive licence) · get_code("3cb5748b00b30bf8") |
| one_paragraph | Ran | sjj1017/citekit/methods/ALCE_interact.py code served (permissive licence) · get_code("87f7647683a35e3a") |
| strong_one_paragraph | Ran | sjj1017/citekit/citekit/utils/utils.py code served (permissive licence) · get_code("9fea39427c8a945f") |
| compute_mauve | Not yet run | sjj1017/citekit/citekit/evaluator/evaluator.py code served (permissive licence) · get_code("53077c3e14202ce3") |
| entail | Not yet run | sjj1017/citekit/citekit/evaluator/evaluator.py code served (permissive licence) · get_code("99ba7cd8c943a75c") |
| load_model | Not yet run | sjj1017/citekit/citekit/cite_modules/LLM.py code served (permissive licence) · get_code("2b1aa6c33e7b0d55") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Enabling Large Language Models (LLMs) to generate citations in Question-Answering (QA) tasks is an emerging paradigm aimed at enhancing the verifiability of their responses when LLMs are utilizing external references to generate an answer. However, there is currently no unified framework to standardize and fairly compare different citation generation methods, leading to difficulties in reproducing different methods and a comprehensive assessment. To cope with the problems above, we introduce \name, an open-source and modular toolkit designed to facilitate the implementation and evaluation of existing citation generation methods, while also fostering the development of new approaches to improve citation quality in LLM outputs. This tool is highly extensible, allowing users to utilize 4 main modules and 14 components to construct a pipeline, evaluating an existing method or innovative designs. Our experiments with two state-of-the-art LLMs and 11 citation generation baselines demonstrate varying strengths of different modules in answer accuracy and citation quality improvement, as well as the challenge of enhancing granularity. Based on our analysis of the effectiveness of components, we propose a new method, self-RAG \snippet, obtaining a balanced answer accuracy and citation quality. Citekit is released at https://github.com/SjJ1017/Citekit.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.04662")
get_code_for_paper("2408.04662")
have("2408.04662")
Connect an agent — have() is free.