{"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/risk-averse-finetuning-of-large-language","title":"Risk-Averse Finetuning of Large Language Models","arxiv_id":"2501.06911","date":"2025-01-12","proceeding":null,"authors":["Sapana Chaudhary","Ujwal Dinesha","Dileep Kalathil","Srinivas Shakkottai"],"abstract":"We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-averse principles into LLM fine-tuning to minimize the occurrence of harmful outputs, particularly rare but significant events. By optimizing the risk measure of Conditional Value at Risk (CVaR), our methodology trains LLMs to exhibit superior performance in avoiding toxic outputs while maintaining effectiveness in generative tasks. Empirical evaluations on sentiment modification and toxicity mitigation tasks demonstrate the efficacy of risk-averse reinforcement learning with human feedback (RLHF) in promoting a safer and more constructive online discourse environment.","url_abs":"https://arxiv.org/abs/2501.06911v1","url_pdf":"https://arxiv.org/pdf/2501.06911v1.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":"risk-averse-finetuning-of-large-language","repo_url":"https://github.com/sapanachaudhary/ra-rlhf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.06911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06911"}},"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/sapanachaudhary/ra-rlhf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"8483cffb5dea03d2","entry":"convert_to_scalar","repo":"sapanachaudhary/ra-rlhf","repo_kind":"official","path":"trl/core.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/core.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8483cffb5dea03d2"}},{"code_sha256_prefix":"7dc16cc69c54c94d","entry":"stack_dicts","repo":"sapanachaudhary/ra-rlhf","repo_kind":"official","path":"trl/core.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/core.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7dc16cc69c54c94d"}},{"code_sha256_prefix":"1782ce5551146615","entry":"flatten_dict","repo":"sapanachaudhary/ra-rlhf","repo_kind":"official","path":"trl/core.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/core.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":"1782ce5551146615"}},{"code_sha256_prefix":"d6e962139d6c0dec","entry":"run_experiment","repo":"sapanachaudhary/ra-rlhf","repo_kind":"official","path":"benchmark/benchmark.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/benchmark/benchmark.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":"d6e962139d6c0dec"}},{"code_sha256_prefix":"55a252ad77e7e399","entry":"scheduler_step","repo":"sapanachaudhary/ra-rlhf","repo_kind":"official","path":"trl/models/modeling_sd_base.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/models/modeling_sd_base.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":"55a252ad77e7e399"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}