Papers › Episodic Memories Generation and Evaluation Benchmark for Large Language Models

Episodic Memories Generation and Evaluation Benchmark for Large Language Models

21 Jan 2025arXiv:2501.13121archive 2025-07-28

Alexis Huet, Zied Ben Houidi, Dario Rossi

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 13 ran (13 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ahstat/episodic-memory-benchmark officialmentioned in papermentioned on GitHubMITSyntology: 14 samples, 13 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran
1unverified

Licence: 14 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ahstat/episodic-memory-benchmark. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ahstat/episodic-memory-benchmark official repository 14 samples, 13 ran (0 instrument-failed) · 1 unverified
append_number_if_duplicate epbench/src/evaluation/scoring_answers.py ran MIT recorded; this copy not marked cleared · pointer only · f7b7adaede9c1cc0 · report fixture: signature mylist_in:Tensor/1/int · returned list · level recorded 2026-09-24
check_and_remove epbench/src/evaluation/generator_answers_1_prompting.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 24de7d7bf124988c · report fixture: signature book:str/0/str, substring:str/0/str, error_if_not_found:bool/0/bool · returned str · level recorded 2026-09-25
convert_uncertainty_format epbench/src/evaluation/ranking.py ran MIT recorded; this copy not marked cleared · pointer only · b57fd480e6da09ab · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-24
f1_score_func epbench/src/evaluation/scoring_answers.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · de963d0285a5664a · report fixture: signature precision:float/0/float, recall:float/0/float · returned float · level recorded 2026-09-24
generate_episodic_memory_prompt epbench/src/evaluation/prompts.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 9418d2d478ea0305 · report fixture: signature book_content:str/0/str, question:str/0/str · returned str · level recorded 2026-09-25
generate_episodic_memory_rag_prompt epbench/src/evaluation/generator_answers_2_rag.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 15280c4c08144e4a · report fixture: signature book_content:str/0/str, question:str/0/str · returned str · level recorded 2026-09-25
get_short_name in 6 papers epbench/src/evaluation/ranking.py ran MIT recorded; this copy not marked cleared · pointer only · b0421b36bcc3addb · report fixture: signature i:int/0/int, df:DataFrame/0/? · returned str · level recorded 2026-09-25
get_short_name_from_model_name epbench/src/evaluation/ranking.py ran MIT recorded; this copy not marked cleared · pointer only · 76180a167954eebf · report fixture: signature answering_model_name:str/0/str, answering_kind:str/0/str, answering_embedding_chunk:str/0/str · returned str · level recorded 2026-09-24
iteration_verbose_func epbench/src/generation/generate_2_paragraph.py ran MIT recorded; this copy not marked cleared · pointer only · 58fd52aa3c394c45 · report fixture: signature i:int/0/int, has_direct_verif_vector:list/1/bool, final:bool/0/bool · returned str · level recorded 2026-09-25
judge_prompt_func epbench/src/evaluation/scoring_answers.py ran MIT recorded; this copy not marked cleared · pointer only · 5822f5812826c314 · report fixture: signature retrieval_type:str/0/str, correct_answer:list/1/str, llm_answer:str/0/str, correct_answer_long:str/0/str · returned str · level recorded 2026-09-24
retrieve_fileid epbench/src/evaluation/generator_answers_3_ftuning.py ran MIT recorded; this copy not marked cleared · pointer only · 8a70f9eda3e9c541 · report fixture: signature client:MockFileClient/0/?, jsonl_filename:str/0/str · returned str · level recorded 2026-09-24
upload_ftuning_input epbench/src/evaluation/generator_answers_3_ftuning.py ran MIT recorded; this copy not marked cleared · pointer only · 56554feb5a10d6e4 · report fixture: returned int · level recorded 2026-09-24
whether_do_this_q epbench/src/evaluation/generator_answers_1_prompting.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 7bb43402032a22a1 · report fixture: signature q:int/0/int, q_max:int/0/int · returned bool · level recorded 2026-09-24
patch_for_ensuring_token_size_lower_130k_in_llama3 epbench/src/evaluation/generator_answers_1_prompting.py unverified MIT recorded; this copy not marked cleared · pointer only · 415511e9a094dd88 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4LLaMALabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections