{"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/fast-and-robust-early-exiting-framework-for","title":"Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding","arxiv_id":"2310.05424","date":"2023-10-09","proceeding":null,"authors":["Sangmin Bae","Jongwoo Ko","Hwanjun Song","Se-Young Yun"],"abstract":"To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token. However, we observed several shortcomings, including performance degradation caused by a state copying mechanism or numerous exit paths, and sensitivity to exit confidence thresholds. Consequently, we propose a Fast and Robust Early-Exiting (FREE) framework, which incorporates a shallow-deep module and a synchronized parallel decoding. Our framework enables faster inference by synchronizing the decoding process of the current token with previously stacked early-exited tokens. Furthermore, as parallel decoding allows us to observe predictions from both shallow and deep models, we present a novel adaptive threshold estimator that exploits a Beta mixture model to determine suitable confidence thresholds. We empirically demonstrated the superiority of our proposed framework on extensive generation tasks.","url_abs":"https://arxiv.org/abs/2310.05424v1","url_pdf":"https://arxiv.org/pdf/2310.05424v1.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":"fast-and-robust-early-exiting-framework-for","repo_url":"https://github.com/raymin0223/fast_robust_early_exit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-and-robust-early-exiting-framework-for","repo_url":"https://github.com/matteonulli/vocabulary_pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.05424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05424"}},"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/raymin0223/fast_robust_early_exit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/matteonulli/vocabulary_pruning","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":10,"samples":[{"code_sha256_prefix":"d67786f4cfb14924","entry":"BetaMixture1D","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d67786f4cfb14924"}},{"code_sha256_prefix":"ccd915435d0afe4e","entry":"DeployT5Attention","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccd915435d0afe4e"}},{"code_sha256_prefix":"e434df9bf6f6dd15","entry":"get_confidence_class","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e434df9bf6f6dd15"}},{"code_sha256_prefix":"5f5c27cd78c9f54f","entry":"meta_confidence","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f5c27cd78c9f54f"}},{"code_sha256_prefix":"b7e7c517d05b34a9","entry":"softmax_confidence","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7e7c517d05b34a9"}},{"code_sha256_prefix":"d87121cce6a345cb","entry":"DeployT5Block","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d87121cce6a345cb"}},{"code_sha256_prefix":"9671b2ac9313a659","entry":"DeployT5LayerCrossAttention","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9671b2ac9313a659"}},{"code_sha256_prefix":"936a20e20a57db3c","entry":"DeployT5LayerSelfAttention","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"936a20e20a57db3c"}},{"code_sha256_prefix":"8a46ec33c5be0782","entry":"DeployT5Stack","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a46ec33c5be0782"}},{"code_sha256_prefix":"eda4f8d14af2f688","entry":"get_skip_mask","repo":"raymin0223/fast_robust_early_exit","repo_kind":"official","path":"models/deploying_t5.py","file_url":"https://github.com/raymin0223/fast_robust_early_exit/blob/HEAD/models/deploying_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eda4f8d14af2f688"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}