SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.09044 · EMNLP · 2023

KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

Yangqiu Song, Tianqing Fang, Zhaowei Wang, Sehyun Choi

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2310.09044.json · badge: /api/ran/2310.09044.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
hkust-knowcomp/knowledge-constrained-decoding marked official in Papers with Code
Papers with Code archive
3 ran · 2 no recorded run
FunctionStatusWhere it lives
MetricGuidance Ran
ran on a synthesized input
hkust-knowcomp/knowledge-constrained-decoding/kcd/classifier_guidance/ppl_mcts.py
pointer only (licence: NONE) · get_code("cb174a2447483b88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-knowcomp/knowledge-constrained-decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_sequences_to_left Ran
ran, honoured the contract we drafted
hkust-knowcomp/knowledge-constrained-decoding/kcd/classifier_guidance/ppl_mcts.py
pointer only (licence: NONE) · get_code("a20af491d8ea2dde")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-knowcomp/knowledge-constrained-decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_sequences_to_left_states Ran
ran; our contract draft was wrong, not the code
hkust-knowcomp/knowledge-constrained-decoding/kcd/classifier_guidance/ppl_mcts.py
pointer only (licence: NONE) · get_code("887918dc48c0319a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-knowcomp/knowledge-constrained-decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LMStep Not yet run
unverified (harvested, no recorded run)
hkust-knowcomp/knowledge-constrained-decoding/kcd/classifier_guidance/ppl_mcts.py
pointer only (licence: NONE) · get_code("e6aa43ab8fd9a4aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-knowcomp/knowledge-constrained-decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

PplMCTS Not yet run
unverified (harvested, no recorded run)
hkust-knowcomp/knowledge-constrained-decoding/kcd/classifier_guidance/ppl_mcts.py
pointer only (licence: NONE) · get_code("5e3af55d43323dd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-knowcomp/knowledge-constrained-decoding when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
pad_sequences_to_left
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2109.13582 (2021-09)
PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) have demonstrated remarkable human-level natural language generation capabilities. However, their potential to generate misinformation, often called the hallucination problem, poses a significant risk to their deployment. A common approach to address this issue is to retrieve relevant knowledge and fine-tune the LLM with the knowledge in its input. Unfortunately, this method incurs high training costs and may cause catastrophic forgetting for multitasking models. To overcome these limitations, we propose a knowledge-constrained decoding method called KCTS (Knowledge-Constrained Tree Search), which guides a frozen LM to generate text aligned with the reference knowledge at each decoding step using a knowledge classifier score and MCTS (Monte-Carlo Tree Search). To adapt the sequence-level knowledge classifier to token-level guidance, we also propose a novel token-level hallucination detection method called RIPA (Reward Inflection Point Approximation). Our empirical results on knowledge-grounded dialogue and abstractive summarization demonstrate the strength of KCTS 1 as a plug-and-play, model-agnostic decoding method that can effectively reduce hallucinations in natural language generation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.09044")
get_code_for_paper("2310.09044")
have("2310.09044")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.09044.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.09044.svg)](https://syntology.ai/paper/2310.09044)

Connect an agent — have() is free.