Papers › SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning

SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning

24 Jan 2024arXiv:2401.13246archive 2025-07-28

Guoxin Chen, Kexin Tang, Chao Yang, Fuying Ye, Yu Qiao, Yiming Qian

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured explanations demand models to perform intricately structured reasoning, which poses great challenges. Most existing methods focus on single-step reasoning through supervised learning, ignoring logical dependencies between steps. Moreover, existing reinforcement learning (RL) based methods overlook the structured relationships, underutilizing the potential of RL in structured reasoning. In this paper, we propose SEER, a novel method that maximizes a structure-based return to facilitate structured reasoning and explanation. Our proposed structure-based return precisely describes the hierarchical and branching structure inherent in structured reasoning, effectively capturing the intricate relationships between different reasoning steps. In addition, we introduce a fine-grained reward function to meticulously delineate diverse reasoning steps. Extensive experiments show that SEER significantly outperforms state-of-the-art methods, achieving an absolute improvement of 6.9% over RL-based methods on EntailmentBank, a 4.4% average improvement on STREET benchmark, and exhibiting outstanding efficiency and cross-dataset generalization performance. Our code is available at https://github.com/Chen-GX/SEER.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2401.13246")

Code

Syntology Ran 13 of 16 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · violated contract; 5 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 12 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chen-gx/seer officialmentioned in papermentioned on GitHubpytorchMIT 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

16 samples harvested; 13 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
5ran · our draft was wrong
7ran
3unverified

Licence: 1 of the 16 samples is 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 Chen-GX/SEER. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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 “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

add_fullstop Chen-GX/SEER/etree_task1/src/RL_etree.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 37840dac8fbe9984 · report
check_nan_and_inf chen-gx/seer/etree_task1/src/policy_net.py official repository ran fingerprinted MIT (permissive) · f327a42b68b8350d · report
decapitalize Chen-GX/SEER/etree_task1/src/RL_etree.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 97e18d0b698dd4c8 · report
get_task1 chen-gx/seer/etree_task1/src/utils.py official repository ran MIT (permissive) · 2876f6baff3466a8 · report
get_task2 chen-gx/seer/etree_task1/src/utils.py official repository ran MIT (permissive) · 2809af8aa84d6463 · report
load_data chen-gx/seer/etree_task1/src/utils.py official repository ran MIT (permissive) · 91ef4f10af2f0360 · report
normalize Chen-GX/SEER/etree_task1/src/RL_etree.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · cf0a06f7868d1697 · report
normalize_sentence chen-gx/seer/etree_task1/src/reward.py official repository ran fingerprinted MIT (permissive) · 687eee6f12fa2fbe · report
parse_entailment_step_proof chen-gx/seer/etree_task1/src/reward.py official repository ran MIT (permissive) · 07b94a2626ece603 · report
same_sent Chen-GX/SEER/etree_task1/src/RL_etree.py official repository ran · violated contract fingerprinted MIT (permissive) · 252ca6659b772750 · report
sort_key Chen-GX/SEER/etree_task1/src/RL_etree.py official repository ran · our draft was wrong MIT (permissive) · 5218be161f3c9262 · report
str2bool chen-gx/seer/etree_task1/src/arguments.py official repository ran MIT (permissive) · 92a5f0d0912c3a91 · report
State Chen-GX/SEER/etree_task1/src/RL_etree.py official repository unverified MIT (permissive) · 7dab5599647f8485 · report
eTree Chen-GX/SEER/etree_task1/src/RL_etree.py official repository unverified MIT (permissive) · 01ce62aa5e1a87d2 · report
score_aligned_entail_tree_proof chen-gx/seer/etree_task1/src/reward.py official repository unverified MIT (permissive) · 27dff68f0e4774cb · report
normalize_answer identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · e7e75981cb464788 · report

Tasks

Question AnsweringReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionCosine AnnealingDense ConnectionsFocusGlobal Average PoolingGrouped ConvolutionLARSReLURegNetYSEERSigmoid ActivationSqueeze-and-Excitation BlockSwAV

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