{"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/esc-judge-a-framework-for-comparing-emotional","title":"ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents","arxiv_id":"2505.12531","date":"2025-05-18","proceeding":null,"authors":["Navid Madani","Rohini Srihari"],"abstract":"Large language models (LLMs) increasingly power mental-health chatbots, yet the field still lacks a scalable, theory-grounded way to decide which model is most effective to deploy. We present ESC-Judge, the first end-to-end evaluation framework that (i) grounds head-to-head comparisons of emotional-support LLMs in Clara Hill's established Exploration-Insight-Action counseling model, providing a structured and interpretable view of performance, and (ii) fully automates the evaluation pipeline at scale. ESC-Judge operates in three stages: first, it synthesizes realistic help-seeker roles by sampling empirically salient attributes such as stressors, personality, and life history; second, it has two candidate support agents conduct separate sessions with the same role, isolating model-specific strategies; and third, it asks a specialized judge LLM to express pairwise preferences across rubric-anchored skills that span the Exploration, Insight, and Action spectrum. In our study, ESC-Judge matched PhD-level annotators on 85 percent of Exploration, 83 percent of Insight, and 86 percent of Action decisions, demonstrating human-level reliability at a fraction of the cost. All code, prompts, synthetic roles, transcripts, and judgment scripts are released to promote transparent progress in emotionally supportive AI.","url_abs":"https://arxiv.org/abs/2505.12531v1","url_pdf":"https://arxiv.org/pdf/2505.12531v1.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":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.12531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12531"}},"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/navidmdn/ESC-Judge","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":14},"by_repo_kind":{"found_in_text":{"samples":14,"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":"79b0e4143f36738c","entry":"get_model_response","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"hf_persona_based_chat.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/hf_persona_based_chat.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":"79b0e4143f36738c"}},{"code_sha256_prefix":"9cdaae1ea22a36e7","entry":"get_openai_chat_prompt","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"langchain_persona_based_chat.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/langchain_persona_based_chat.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":"9cdaae1ea22a36e7"}},{"code_sha256_prefix":"fc250ec0f3ccbc34","entry":"group_conversations","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"merge_and_judge.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/merge_and_judge.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":"fc250ec0f3ccbc34"}},{"code_sha256_prefix":"dd20d05a85fb7631","entry":"load_json","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"multidim_judge_from_merged.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/multidim_judge_from_merged.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":"dd20d05a85fb7631"}},{"code_sha256_prefix":"720f3f0012bdfd66","entry":"load_jsonl","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"multidim_judge_from_merged.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/multidim_judge_from_merged.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":"720f3f0012bdfd66"}},{"code_sha256_prefix":"885cdf0c8392f181","entry":"load_jsonl","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"multidim_geval.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/multidim_geval.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":"885cdf0c8392f181"}},{"code_sha256_prefix":"19801924b3c90395","entry":"load_llama3_model","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"hf_persona_based_chat.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/hf_persona_based_chat.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":"19801924b3c90395"}},{"code_sha256_prefix":"697984d1d7fb77ff","entry":"load_prompt_constructor","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"langchain_persona_based_chat.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/langchain_persona_based_chat.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":"697984d1d7fb77ff"}},{"code_sha256_prefix":"0d5383d390821c06","entry":"load_text","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"merge_and_judge.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/merge_and_judge.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":"0d5383d390821c06"}},{"code_sha256_prefix":"86dd2dbd49ecbcd4","entry":"load_text","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"multidim_geval.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/multidim_geval.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":"86dd2dbd49ecbcd4"}},{"code_sha256_prefix":"4db0bfe2bd8f8d91","entry":"parse_filename","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"merge_and_judge.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/merge_and_judge.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":"4db0bfe2bd8f8d91"}},{"code_sha256_prefix":"7a9173a15ddc701b","entry":"sample_behavior_trait_string","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"fixed_challenge_characteristic_prompts.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/fixed_challenge_characteristic_prompts.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":"7a9173a15ddc701b"}},{"code_sha256_prefix":"d81cf829f72f5f7f","entry":"sample_gender","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"fixed_challenge_characteristic_prompts.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/fixed_challenge_characteristic_prompts.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":"d81cf829f72f5f7f"}},{"code_sha256_prefix":"6e00835f7961d124","entry":"sample_ongoing_challenge_string","repo":"navidmdn/ESC-Judge","repo_kind":"found_in_text","path":"fixed_challenge_characteristic_prompts.py","file_url":"https://github.com/navidmdn/ESC-Judge/blob/HEAD/fixed_challenge_characteristic_prompts.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":"6e00835f7961d124"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}