Papers › Knowledge-Augmented Language Model Verification

Knowledge-Augmented Language Model Verification

19 Oct 2023arXiv:2310.12836archive 2025-07-28

Jinheon Baek, Soyeong Jeong, Minki Kang, Jong C. Park, Sung Ju Hwang

Recent Language Models (LMs) have shown impressive capabilities in generating texts with the knowledge internalized in parameters. Yet, LMs often generate the factually incorrect responses to the given queries, since their knowledge may be inaccurate, incomplete, and outdated. To address this problem, previous works propose to augment LMs with the knowledge retrieved from an external knowledge source. However, such approaches often show suboptimal text generation performance due to two reasons: 1) the model may fail to retrieve the knowledge relevant to the given query, or 2) the model may not faithfully reflect the retrieved knowledge in the generated text. To overcome these, we propose to verify the output and the knowledge of the knowledge-augmented LMs with a separate verifier, which is a small LM that is trained to detect those two types of errors through instruction-finetuning. Then, when the verifier recognizes an error, we can rectify it by either retrieving new knowledge or generating new text. Further, we use an ensemble of the outputs from different instructions with a single verifier to enhance the reliability of the verification processes. We validate the effectiveness of the proposed verification steps on multiple question answering benchmarks, whose results show that the proposed verifier effectively identifies retrieval and generation errors, allowing LMs to provide more factually correct outputs. Our code is available at https://github.com/JinheonBaek/KALMV.

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="2310.12836")

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: 2 ran · honoured contract; 4 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jinheonbaek/kalmv officialmentioned in papermentioned on GitHubpytorch 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; 2 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.

2ran · honoured contract
4ran · our draft was wrong
7ran
3unverified

Licence: 16 of the 16 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 JinheonBaek/KALMV. “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.

accuracy JinheonBaek/KALMV/models/verifiers.py official repository ran no licence file found · pointer only · 546e0e6bff195e94 · report
compute_exact jinheonbaek/kalmv/metrics.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 9026d9da5d085bd4 · report
compute_exact JinheonBaek/KALMV/models/verifiers.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 66722e30b46133ad · report
convert_orign_to_jsonl jinheonbaek/kalmv/preprocess/process_odqa.py official repository ran no licence file found · pointer only · 32f7ecc05ecdb661 · report
em JinheonBaek/KALMV/models/verifiers.py official repository ran no licence file found · pointer only · 008bf270c07cb383 · report
f1 JinheonBaek/KALMV/models/verifiers.py official repository ran no licence file found · pointer only · d8906dbc7552ff58 · report
get_answer jinheonbaek/kalmv/preprocess/process_odqa.py official repository ran no licence file found · pointer only · 2472555bb4ad6b7e · report
get_qa_datasets jinheonbaek/kalmv/data.py official repository ran no licence file found · pointer only · 0e30c99e9be65f47 · report
get_question jinheonbaek/kalmv/preprocess/process_odqa.py official repository ran no licence file found · pointer only · a6f87877056e2eb3 · report
get_tokens jinheonbaek/kalmv/metrics.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · aa6bc32d9c17a2f1 · report
get_tokens JinheonBaek/KALMV/models/verifiers.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · a2c23eaf23140be2 · report
normalize_answer jinheonbaek/kalmv/metrics.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 6a96435eba311b08 · report
normalize_answer JinheonBaek/KALMV/models/verifiers.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 4d2f27c630abe8bf · report
Verifier JinheonBaek/KALMV/models/verifiers.py official repository unverified no licence file found · pointer only · 96d5fd97997163de · report
Verifier_KG JinheonBaek/KALMV/models/verifiers.py official repository unverified no licence file found · pointer only · 1d5602144651adc3 · report
compute_f1 JinheonBaek/KALMV/models/verifiers.py official repository unverified no licence file found · pointer only · b004a421a9a1ba54 · report

Tasks

Language ModelingLanguage ModellingQuestion AnsweringText Generationmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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