{"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/not-all-tokens-are-what-you-need-in-thinking","title":"Not All Tokens Are What You Need In Thinking","arxiv_id":"2505.17827","date":"2025-05-23","proceeding":null,"authors":["Hang Yuan","Bin Yu","Haotian Li","Shijun Yang","Christina Dan Wang","Zhou Yu","Xueyin Xu","Weizhen Qi","Kai Chen"],"abstract":"Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency toward overthinking -- generating verbose chains of thought (CoT) laden with redundant tokens that contribute minimally to the final answer. To address these issues, we propose Conditional Token Selection (CTS), a token-level compression framework with a flexible and variable compression ratio that identifies and preserves only the most essential tokens in CoT. CTS evaluates each token's contribution to deriving correct answers using conditional importance scoring, then trains models on compressed CoT. Extensive experiments demonstrate that CTS effectively compresses long CoT while maintaining strong reasoning performance. Notably, on the GPQA benchmark, Qwen2.5-14B-Instruct trained with CTS achieves a 9.1% accuracy improvement with 13.2% fewer reasoning tokens (13% training token reduction). Further reducing training tokens by 42% incurs only a marginal 5% accuracy drop while yielding a 75.8% reduction in reasoning tokens, highlighting the prevalence of redundancy in existing CoT.","url_abs":"https://arxiv.org/abs/2505.17827v1","url_pdf":"https://arxiv.org/pdf/2505.17827v1.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":"not-all-tokens-are-what-you-need-in-thinking","repo_url":"https://github.com/faustrazor/not-all-thinking-tokens","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"token-reduction","task_name":"Token Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.17827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17827"}},"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/faustrazor/not-all-thinking-tokens","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"489ef2bf76b5d32c","entry":"agg_mean_length","repo":"faustrazor/not-all-thinking-tokens","repo_kind":"official","path":"CTS/test_src/lighteval-llm/src/eval/eval_aime.py","file_url":"https://github.com/faustrazor/not-all-thinking-tokens/blob/HEAD/CTS/test_src/lighteval-llm/src/eval/eval_aime.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"489ef2bf76b5d32c"}},{"code_sha256_prefix":"54d4945919c751a4","entry":"compute_sample_length","repo":"faustrazor/not-all-thinking-tokens","repo_kind":"official","path":"CTS/test_src/lighteval-llm/src/eval/eval_aime.py","file_url":"https://github.com/faustrazor/not-all-thinking-tokens/blob/HEAD/CTS/test_src/lighteval-llm/src/eval/eval_aime.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"54d4945919c751a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}