{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/peek-across-improving-multi-document-modeling","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","arxiv_id":"2305.15387","date":"2023-05-24","proceeding":null,"authors":["Avi Caciularu","Matthew E. Peters","Jacob Goldberger","Ido Dagan","Arman Cohan"],"abstract":"The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. To that end, given a set (or cluster) of topically-related documents, we systematically generate semantically-oriented questions from a salient sentence in one document and challenge the model, during pre-training, to answer these questions while \"peeking\" into other topically-related documents. In a similar manner, the model is also challenged to recover the sentence from which the question was generated, again while leveraging cross-document information. This novel multi-document QA formulation directs the model to better recover cross-text informational relations, and introduces a natural augmentation that artificially increases the pre-training data. Further, unlike prior multi-document models that focus on either classification or summarization tasks, our pre-training objective formulation enables the model to perform tasks that involve both short text generation (e.g., QA) and long text generation (e.g., summarization). Following this scheme, we pre-train our model -- termed QAmden -- and evaluate its performance across several multi-document tasks, including multi-document QA, summarization, and query-focused summarization, yielding improvements of up to 7%, and significantly outperforms zero-shot GPT-3.5 and GPT-4.","url_abs":"https://arxiv.org/abs/2305.15387v1","url_pdf":"https://arxiv.org/pdf/2305.15387v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"peek-across-improving-multi-document-modeling","repo_url":"https://github.com/aviclu/peekacross","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"query-focused-summarization","task_name":"Query-focused Summarization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.15387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15387"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aviclu/peekacross","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":17},"by_repo_kind":{"official":{"samples":18,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5e9a5fc2ab282ff2","entry":"label_smoothed_nll_loss","repo":"aviclu/peekacross","repo_kind":"official","path":"finetune_summarization.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/finetune_summarization.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e9a5fc2ab282ff2"}},{"code_sha256_prefix":"dd5fe1a76839bea4","entry":"collate_fn","repo":"aviclu/peekacross","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd5fe1a76839bea4"}},{"code_sha256_prefix":"7dc4c3b7d24d7a61","entry":"compute_rouge_scores","repo":"aviclu/peekacross","repo_kind":"official","path":"compute_scores.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/compute_scores.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7dc4c3b7d24d7a61"}},{"code_sha256_prefix":"827e0090858aabdc","entry":"compute_scores","repo":"aviclu/peekacross","repo_kind":"official","path":"compute_scores.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/compute_scores.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"827e0090858aabdc"}},{"code_sha256_prefix":"8fad2994edad57e5","entry":"exact_match_score","repo":"aviclu/peekacross","repo_kind":"official","path":"trainer_seq2seq_qa.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/trainer_seq2seq_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8fad2994edad57e5"}},{"code_sha256_prefix":"e3ad4a101c45630f","entry":"f1_score","repo":"aviclu/peekacross","repo_kind":"official","path":"trainer_seq2seq_qa.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/trainer_seq2seq_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3ad4a101c45630f"}},{"code_sha256_prefix":"0ddc90e33f8f62f2","entry":"get_dataloader_pretrain","repo":"aviclu/peekacross","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ddc90e33f8f62f2"}},{"code_sha256_prefix":"389f2c92478eb394","entry":"get_dataloader_summ","repo":"aviclu/peekacross","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"389f2c92478eb394"}},{"code_sha256_prefix":"1ee9eda681e11e7b","entry":"get_doc_sep_token","repo":"aviclu/peekacross","repo_kind":"official","path":"pretrain_qamden.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/pretrain_qamden.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ee9eda681e11e7b"}},{"code_sha256_prefix":"58fc74bade60d243","entry":"get_entities","repo":"aviclu/peekacross","repo_kind":"official","path":"compute_scores.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/compute_scores.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58fc74bade60d243"}},{"code_sha256_prefix":"45a54c7c02b59ae7","entry":"get_global_attention_mask","repo":"aviclu/peekacross","repo_kind":"official","path":"pretrain_qamden.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/pretrain_qamden.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45a54c7c02b59ae7"}},{"code_sha256_prefix":"83cfdd6d3dfa70e0","entry":"normalize_answer","repo":"aviclu/peekacross","repo_kind":"official","path":"trainer_seq2seq_qa.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/trainer_seq2seq_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83cfdd6d3dfa70e0"}},{"code_sha256_prefix":"82c9ae018e16d079","entry":"remove_all_extra_spaces","repo":"aviclu/peekacross","repo_kind":"official","path":"preprocess_and_filter_data.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/preprocess_and_filter_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82c9ae018e16d079"}},{"code_sha256_prefix":"7999a2027aeca45a","entry":"remove_end_spaces","repo":"aviclu/peekacross","repo_kind":"official","path":"preprocess_and_filter_data.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/preprocess_and_filter_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7999a2027aeca45a"}},{"code_sha256_prefix":"12249aea6ac3655c","entry":"remove_first_end_spaces","repo":"aviclu/peekacross","repo_kind":"official","path":"preprocess_and_filter_data.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/preprocess_and_filter_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12249aea6ac3655c"}},{"code_sha256_prefix":"31e3adacd2841d84","entry":"sanitize_text","repo":"aviclu/peekacross","repo_kind":"official","path":"pretrain_qamden.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/pretrain_qamden.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31e3adacd2841d84"}},{"code_sha256_prefix":"6f751053716f926f","entry":"select_sent_with_entities","repo":"aviclu/peekacross","repo_kind":"official","path":"pretrain_preprocess_qasem.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/pretrain_preprocess_qasem.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f751053716f926f"}},{"code_sha256_prefix":"8c7c0e3aca247bef","entry":"select_sent_with_entities_per_doc","repo":"aviclu/peekacross","repo_kind":"official","path":"pretrain_preprocess_qasem.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/pretrain_preprocess_qasem.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c7c0e3aca247bef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}