Papers › Large Language Models are Temporal and Causal Reasoners for Video Question Answering

Large Language Models are Temporal and Causal Reasoners for Video Question Answering

24 Oct 2023arXiv:2310.15747archive 2025-07-28

Dohwan Ko, Ji Soo Lee, Wooyoung Kang, Byungseok Roh, Hyunwoo J. Kim

Large Language Models (LLMs) have shown remarkable performances on a wide range of natural language understanding and generation tasks. We observe that the LLMs provide effective priors in exploiting linguistic shortcuts for temporal and causal reasoning in Video Question Answering (VideoQA). However, such priors often cause suboptimal results on VideoQA by leading the model to over-rely on questions, i.e., linguistic bias, while ignoring visual content. This is also known as `ungrounded guesses' or `hallucinations'. To address this problem while leveraging LLMs' prior on VideoQA, we propose a novel framework, Flipped-VQA, encouraging the model to predict all the combinations of ⟨V, Q, A⟩ triplet by flipping the source pair and the target label to understand their complex relationships, i.e., predict A, Q, and V given a VQ, VA, and QA pairs, respectively. In this paper, we develop LLaMA-VQA by applying Flipped-VQA to LLaMA, and it outperforms both LLMs-based and non-LLMs-based models on five challenging VideoQA benchmarks. Furthermore, our Flipped-VQA is a general framework that is applicable to various LLMs (OPT and GPT-J) and consistently improves their performances. We empirically demonstrate that Flipped-VQA not only enhances the exploitation of linguistic shortcuts but also mitigates the linguistic bias, which causes incorrect answers over-relying on the question. Code is available at https://github.com/mlvlab/Flipped-VQA.

PaperPDFCodeCode Syntology ranMethod as code

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 4 code samples harvested from 1 repository linked to this paper: 0 ran · 4 unverified.

By repository: official repository: 4 samples from 1 repository, 0 ran (0 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.

mlvlab/Flipped-VQA officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 0 ran · 4 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

4 samples harvested: 0 ran · 4 unverified. 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.

4unverified

Licence: 0 of the 4 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 mlvlab/Flipped-VQA. “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. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mlvlab/Flipped-VQA official repository 4 samples, 0 ran · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
llama/model.py unverified MIT (permissive) · ea4fa90ff313cb77 · report
ModelArgs in 13 papers llama/model.py unverified MIT (permissive) · 6f671e3b713c8c1b · report
Transformer in 173 papers llama/model.py unverified MIT (permissive) · afd800d945fafd04 · report
TransformerBlock in 73 papers llama/model.py unverified MIT (permissive) · ed5543f646686967 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Flipped-VQA (graph method: Flipped-VQA). 9 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Transformer entry · level 0 · unverified · afd800d945fafd04
  2. ModelArgs model · level 0 · unverified · 6f671e3b713c8c1b
  3. RMSNorm model · level 1 · ran · df852b6b3526e46e
  4. TransformerBlock model · level 0 · unverified · ed5543f646686967
  5. precompute_freqs_cis helper · level 1 · ran · violated contract · 14a84c2cbfebc413
  6. Attention model · level 0 · unverified · ea4fa90ff313cb77
  7. FeedForward model · level 1 · ran · 24ac4d693325d0c3
  8. apply_rotary_emb helper · level 1 · ran; the contract check could not run · b47d48e431b34acd
  9. reshape_for_broadcast helper · level 1 · ran; the contract check could not run · 70bf6ebaafd266c4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2310.15747") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Natural Language UnderstandingQuestion AnsweringVideo Question AnsweringVisual Question Answering (VQA)

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering DramaQA LLaMA-VQA Accuracy 84.1 #1 of 1 Archive leaderboard report
Video Question Answering NExT-QA LLaMA-VQA (33B) Accuracy 75.5 #24 of 47 Archive leaderboard report
Video Question Answering STAR Benchmark LLaMA-VQA Average Accuracy 65.4 #2 of 17 Archive leaderboard report
Video Question Answering TVQA LLaMA-VQA Accuracy 82.2 #1 of 6 Archive leaderboard report
Video Question Answering VLEP LLaMA-VQA Accuracy 71.0 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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