Peng Cui, Mrinmaya Sachan, Xiaoyu Zhang, Vilém Zouhar
We lifted 11 functions out of this paper's own repositories and ran 10 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 |
|---|---|---|
| eth-lre/engage-your-readers | canonical | 10 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| factory_extract_likert | Ran | eth-lre/engage-your-readers/analysis/scripts_main/02-avg_quantitative.py pointer only (licence: NONE) · get_code("7790b46b4d15c025") |
| factory_get_question_likert | Ran | eth-lre/engage-your-readers/analysis/scripts_main/02-avg_quantitative.py pointer only (licence: NONE) · get_code("e990969e3fc2b479") |
| load_by_user | Ran | eth-lre/engage-your-readers/analysis/loader.py pointer only (licence: NONE) · get_code("0c677c8251816be1") |
| load_by_user_prolific | Ran | eth-lre/engage-your-readers/analysis/loader.py pointer only (licence: NONE) · get_code("45565769a4732963") |
| merge_list | Ran | eth-lre/engage-your-readers/src/common_utils.py pointer only (licence: NONE) · get_code("47323200b80f2432") |
| my_collate | Ran | eth-lre/engage-your-readers/src/build_data.py pointer only (licence: NONE) · get_code("5c8d7e5c7eec809d") |
| parse_output | Ran | eth-lre/engage-your-readers/src/common_utils.py pointer only (licence: NONE) · get_code("17f5a8d5d5701f52") |
| remove_dup | Ran | eth-lre/engage-your-readers/src/evaluation.py pointer only (licence: NONE) · get_code("5fbb544ef6e03a0b") |
| uid_to_group | Ran | eth-lre/engage-your-readers/analysis/scripts_main/02-avg_quantitative.py pointer only (licence: NONE) · get_code("590f409e37d1d416") |
| uid_to_group | Ran | eth-lre/engage-your-readers/analysis/scripts_xiaoyu/02-avg_quantitative.py pointer only (licence: NONE) · get_code("8b59243162da2669") |
| map_back | Not yet run | eth-lre/engage-your-readers/src/common_utils.py pointer only (licence: NONE) · get_code("9f0e5dc3876be6ac") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Using questions in written text is an effective strategy to enhance readability. However, what makes an active reading question good, what the linguistic role of these questions is, and what is their impact on human reading remains understudied. We introduce GUIDINGQ, a dataset of 10K in-text questions from textbooks and scientific articles. By analyzing the dataset, we present a comprehensive understanding of the use, distribution, and linguistic characteristics of these questions. Then, we explore various approaches to generate such questions using language models. Our results highlight the importance of capturing inter-question relationships and the challenge of question position identification in generating these questions. Finally, we conduct a human study to understand the implication of such questions on reading comprehension. We find that the generated questions are of high quality and are almost as effective as human-written questions in terms of improving readers' memorization and comprehension. github.com/eth-lre/engage-your-readers How do Philosophers arrive at truth? Is there no quantum form of Einstein Gravity? Why do house-hunting ants recruit in both directions?
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.14309")
get_code_for_paper("2407.14309")
have("2407.14309")
Connect an agent — have() is free.