{"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/language-models-are-hidden-reasoners","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding","arxiv_id":"2411.04282","date":"2024-11-06","proceeding":null,"authors":["Haolin Chen","Yihao Feng","Zuxin Liu","Weiran Yao","Akshara Prabhakar","Shelby Heinecke","Ricky Ho","Phil Mui","Silvio Savarese","Caiming Xiong","Huan Wang"],"abstract":"Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing reasoning capabilities during training remains challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution and optimizes it via variational approaches. LaTRO enables LLMs to concurrently improve both their reasoning process and ability to evaluate reasoning quality, without requiring external feedback or reward models. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures. On GSM8K, LaTRO improves zero-shot accuracy by an average of 12.5% over base models and 9.6% over supervised fine-tuning across Phi-3.5-mini, Mistral-7B, and Llama-3.1-8B. Our findings suggest that pre-trained LLMs possess latent reasoning capabilities that can be unlocked and enhanced through our proposed optimization approach in a self-improvement manner. The code of LaTRO is available at \\url{https://github.com/SalesforceAIResearch/LaTRO}.","url_abs":"https://arxiv.org/abs/2411.04282v2","url_pdf":"https://arxiv.org/pdf/2411.04282v2.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":"language-models-are-hidden-reasoners","repo_url":"https://github.com/salesforceairesearch/latro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"gsm8k","task_name":"GSM8K"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.04282","atlas_url":"https://app.syntology.ai/?focus=2411.04282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04282"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/salesforceairesearch/latro","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":"20063c675d638a77","entry":"is_equiv","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/eval_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20063c675d638a77"}},{"code_sha256_prefix":"c97f58787860b90d","entry":"find_number","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/eval_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/eval_utils.py","link_basis":"first_harvest_node","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":"c97f58787860b90d"}},{"code_sha256_prefix":"600840079aa37cd9","entry":"find_numbers","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/eval_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/eval_utils.py","link_basis":"first_harvest_node","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":"600840079aa37cd9"}},{"code_sha256_prefix":"493d024d8342a0f8","entry":"forward","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/trainer_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/trainer_utils.py","link_basis":"first_harvest_node","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":"493d024d8342a0f8"}},{"code_sha256_prefix":"5cafb313856b17e6","entry":"generate","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/trainer_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/trainer_utils.py","link_basis":"first_harvest_node","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":"5cafb313856b17e6"}},{"code_sha256_prefix":"24f7a5a691bbda88","entry":"get_end_token","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/trainer_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/trainer_utils.py","link_basis":"first_harvest_node","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":"24f7a5a691bbda88"}},{"code_sha256_prefix":"06ec2ff391c7803c","entry":"prepare_dataset_arc","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/data_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/data_utils.py","link_basis":"first_harvest_node","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":"06ec2ff391c7803c"}},{"code_sha256_prefix":"89705e6c0ffce297","entry":"prepare_dataset_gsm8k","repo":"salesforceairesearch/latro","repo_kind":"official","path":"LaTRO/utils/data_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/data_utils.py","link_basis":"first_harvest_node","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":"89705e6c0ffce297"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}