Papers › Re-Reading Improves Reasoning in Large Language Models

Re-Reading Improves Reasoning in Large Language Models

12 Sep 2023arXiv:2309.06275archive 2025-07-28

Xiaohan Xu, Chongyang Tao, Tao Shen, Can Xu, Hongbo Xu, Guodong Long, Jian-Guang Lou, Shuai Ma

To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i.e., \textbf{Re}-\textbf{Re}ading the question as input. Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), which aim to elicit the reasoning process in the output, Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. Consequently, Re2 demonstrates strong generality and compatibility with most thought-eliciting prompting methods, including CoT. Crucially, Re2 facilitates a "bidirectional" encoding in unidirectional decoder-only LLMs because the first pass could provide global information for the second pass. We begin with a preliminary empirical study as the foundation of Re2, illustrating its potential to enable "bidirectional" attention mechanisms. We then evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality. Our findings indicate that, with the exception of a few scenarios on vanilla ChatGPT, Re2 consistently enhances the reasoning performance of LLMs through a simple re-reading strategy. Further analyses reveal Re2's adaptability, showing how it can be effectively integrated with different LLMs, thought-eliciting prompting, and ensemble strategies. Our code is available at \url{https://github.com/Tebmer/Rereading-LLM-Reasoning/}

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="2309.06275")

Code

Syntology Ran 9 of 11 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tebmer/rereading-llm-reasoning officialmentioned in paperApache-2.0 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

11 samples harvested; 9 ran; 0 honoured the contract we drafted; 2 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
2ran · our draft was wrong
6ran
2unverified

Licence: 0 of the 11 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 tebmer/rereading-llm-reasoning. “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.

is_number tebmer/rereading-llm-reasoning/utils/answer_parser.py official repository ran · violated contract Apache-2.0 (permissive) · 0fe9cf6c00ef56ea · report
chat_api tebmer/rereading-llm-reasoning/pal/core/backend.py official repository ran Apache-2.0 (permissive) · 6f07d6fdc179cc59 · report
extract_the_fist_number tebmer/rereading-llm-reasoning/utils/answer_parser.py official repository ran fingerprinted Apache-2.0 (permissive) · 7343bffcd73070da · report
extract_the_last_number tebmer/rereading-llm-reasoning/utils/answer_parser.py official repository ran fingerprinted Apache-2.0 (permissive) · 774cb6f79e4ecf3b · report
last_boxed_only_string tebmer/rereading-llm-reasoning/utils/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0b14c648516c38a7 · report
remove_boxed tebmer/rereading-llm-reasoning/utils/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · f3bbe264b05aadd3 · report
scoere_date_understanding tebmer/rereading-llm-reasoning/utils/scorer.py official repository ran Apache-2.0 (permissive) · 75bdd5a77703b527 · report
scorer_number tebmer/rereading-llm-reasoning/utils/scorer.py official repository ran Apache-2.0 (permissive) · 24602cacdb6ebdb7 · report
scorer_string tebmer/rereading-llm-reasoning/utils/scorer.py official repository ran Apache-2.0 (permissive) · 6e9e8fba2a2d400d · report
call_gpt tebmer/rereading-llm-reasoning/pal/core/backend.py official repository unverified Apache-2.0 (permissive) · d2417be2799a98fe · report
completions_api tebmer/rereading-llm-reasoning/pal/core/backend.py official repository unverified Apache-2.0 (permissive) · 9605ca38ee5df19e · report

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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