{"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/intent-conditioned-and-non-toxic","title":"Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF","arxiv_id":"2403.10088","date":"2024-03-15","proceeding":null,"authors":["Amey Hengle","Aswini Kumar","Sahajpreet Singh","Anil Bandhakavi","Md Shad Akhtar","Tanmoy Chakroborty"],"abstract":"Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. Addressing hate speech effectively involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These implicit expressions challenge language models, especially in seq2seq tasks, as model performance typically excels with longer contexts. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. CoARL's first two phases involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech. The final phase uses reinforcement learning to fine-tune outputs for effectiveness and non-toxicity. CoARL outperforms existing benchmarks in intent-conditioned counterspeech generation, showing an average improvement of 3 points in intent-conformity and 4 points in argument-quality metrics. Extensive human evaluation supports CoARL's efficacy in generating superior and more context-appropriate responses compared to existing systems, including prominent LLMs like ChatGPT.","url_abs":"https://arxiv.org/abs/2403.10088v1","url_pdf":"https://arxiv.org/pdf/2403.10088v1.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":[],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.10088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10088"}},"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":"deterministic:regex_extraction","url":"https://github.com/lvwerra/trl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":10,"ran":9,"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":"6fffb84514770d3e","entry":"get_gamma_weights","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/losses/grpo_loss.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/losses/grpo_loss.py","link_basis":"first_harvest_node","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":"6fffb84514770d3e"}},{"code_sha256_prefix":"dc8b4f56c93e15a4","entry":"has_generation_markers","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/chat_template_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/chat_template_utils.py","link_basis":"first_harvest_node","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":"dc8b4f56c93e15a4"}},{"code_sha256_prefix":"92674d32e9e8fe15","entry":"is_conversational","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/data_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/data_utils.py","link_basis":"first_harvest_node","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":"92674d32e9e8fe15"}},{"code_sha256_prefix":"27029757ccbfdfa1","entry":"is_liger_kernel_available","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/import_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/import_utils.py","link_basis":"first_harvest_node","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":"27029757ccbfdfa1"}},{"code_sha256_prefix":"bea49da00dcdd049","entry":"is_vllm_available","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/import_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/import_utils.py","link_basis":"first_harvest_node","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":"bea49da00dcdd049"}},{"code_sha256_prefix":"86d6504cba39cd87","entry":"k3_loss_fn","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/losses/grpo_loss.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/losses/grpo_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86d6504cba39cd87"}},{"code_sha256_prefix":"db7856b1458fa1c3","entry":"prepare_multimodal_messages","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/data_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/data_utils.py","link_basis":"first_harvest_node","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":"db7856b1458fa1c3"}},{"code_sha256_prefix":"631e70d7b6a27f0f","entry":"prepare_multimodal_messages_vllm","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/data_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/data_utils.py","link_basis":"first_harvest_node","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":"631e70d7b6a27f0f"}},{"code_sha256_prefix":"aa492ab4bceb5b94","entry":"sapo_loss_fn","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/losses/grpo_loss.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/losses/grpo_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa492ab4bceb5b94"}},{"code_sha256_prefix":"cb0eb39dbaf96b03","entry":"clone_chat_template","repo":"lvwerra/trl","repo_kind":"found_in_text","path":"trl/chat_template_utils.py","file_url":"https://github.com/lvwerra/trl/blob/HEAD/trl/chat_template_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":"cb0eb39dbaf96b03"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}