{"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/episodic-memories-generation-and-evaluation","title":"Episodic Memories Generation and Evaluation Benchmark for Large Language Models","arxiv_id":"2501.13121","date":"2025-01-21","proceeding":null,"authors":["Alexis Huet","Zied Ben Houidi","Dario Rossi"],"abstract":"Episodic memory -- the ability to recall specific events grounded in time and space -- is a cornerstone of human cognition, enabling not only coherent storytelling, but also planning and decision-making. Despite their remarkable capabilities, Large Language Models (LLMs) lack a robust mechanism for episodic memory: we argue that integrating episodic memory capabilities into LLM is essential for advancing AI towards human-like cognition, increasing their potential to reason consistently and ground their output in real-world episodic events, hence avoiding confabulations. To address this challenge, we introduce a comprehensive framework to model and evaluate LLM episodic memory capabilities. Drawing inspiration from cognitive science, we develop a structured approach to represent episodic events, encapsulating temporal and spatial contexts, involved entities, and detailed descriptions. We synthesize a unique episodic memory benchmark, free from contamination, and release open source code and datasets to assess LLM performance across various recall and episodic reasoning tasks. Our evaluation of state-of-the-art models, including GPT-4 and Claude variants, Llama 3.1, and o1-mini, reveals that even the most advanced LLMs struggle with episodic memory tasks, particularly when dealing with multiple related events or complex spatio-temporal relationships -- even in contexts as short as 10k-100k tokens.","url_abs":"https://arxiv.org/abs/2501.13121v1","url_pdf":"https://arxiv.org/pdf/2501.13121v1.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":"episodic-memories-generation-and-evaluation","repo_url":"https://github.com/ahstat/episodic-memory-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.13121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13121"}},"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/ahstat/episodic-memory-benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"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":14,"samples":[{"code_sha256_prefix":"f7b7adaede9c1cc0","entry":"append_number_if_duplicate","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/scoring_answers.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/scoring_answers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f7b7adaede9c1cc0"}},{"code_sha256_prefix":"24de7d7bf124988c","entry":"check_and_remove","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/generator_answers_1_prompting.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/generator_answers_1_prompting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"24de7d7bf124988c"}},{"code_sha256_prefix":"b57fd480e6da09ab","entry":"convert_uncertainty_format","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/ranking.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/ranking.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b57fd480e6da09ab"}},{"code_sha256_prefix":"de963d0285a5664a","entry":"f1_score_func","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/scoring_answers.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/scoring_answers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"de963d0285a5664a"}},{"code_sha256_prefix":"9418d2d478ea0305","entry":"generate_episodic_memory_prompt","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/prompts.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/prompts.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9418d2d478ea0305"}},{"code_sha256_prefix":"15280c4c08144e4a","entry":"generate_episodic_memory_rag_prompt","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/generator_answers_2_rag.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/generator_answers_2_rag.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"15280c4c08144e4a"}},{"code_sha256_prefix":"b0421b36bcc3addb","entry":"get_short_name","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/ranking.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/ranking.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b0421b36bcc3addb"}},{"code_sha256_prefix":"76180a167954eebf","entry":"get_short_name_from_model_name","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/ranking.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/ranking.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"76180a167954eebf"}},{"code_sha256_prefix":"58fd52aa3c394c45","entry":"iteration_verbose_func","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/generation/generate_2_paragraph.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/generation/generate_2_paragraph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"58fd52aa3c394c45"}},{"code_sha256_prefix":"5822f5812826c314","entry":"judge_prompt_func","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/scoring_answers.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/scoring_answers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"5822f5812826c314"}},{"code_sha256_prefix":"415511e9a094dd88","entry":"patch_for_ensuring_token_size_lower_130k_in_llama3","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/generator_answers_1_prompting.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/generator_answers_1_prompting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"415511e9a094dd88"}},{"code_sha256_prefix":"8a70f9eda3e9c541","entry":"retrieve_fileid","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/generator_answers_3_ftuning.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/generator_answers_3_ftuning.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"8a70f9eda3e9c541"}},{"code_sha256_prefix":"56554feb5a10d6e4","entry":"upload_ftuning_input","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/generator_answers_3_ftuning.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/generator_answers_3_ftuning.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"56554feb5a10d6e4"}},{"code_sha256_prefix":"7bb43402032a22a1","entry":"whether_do_this_q","repo":"ahstat/episodic-memory-benchmark","repo_kind":"official","path":"epbench/src/evaluation/generator_answers_1_prompting.py","file_url":"https://github.com/ahstat/episodic-memory-benchmark/blob/HEAD/epbench/src/evaluation/generator_answers_1_prompting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"7bb43402032a22a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}