SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.00367 · ACL · 2024

Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

Vidhisha Balachandran, Yulia Tsvetkov, Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding

arXiv · PDF · Open in the Atlas

Code that ran

None of the 1 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (1 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/2402.00367.json · badge: /api/ran/2402.00367.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
bunsenfeng/abstainqa marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
llm_response Not yet run
unverified (harvested, no recorded run)
bunsenfeng/abstainqa/lm_utils.py
pointer only (licence: NONE) · get_code("2b1ebf7b94c18a64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bunsenfeng/abstainqa 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 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Despite efforts to expand the knowledge of large language models (LLMs), knowledge gaps-missing or outdated information in LLMs-might always persist given the evolving nature of knowledge. In this work, we study approaches to identify LLM knowledge gaps and abstain from answering questions when knowledge gaps are present. We first adapt existing approaches to model calibration or adaptation through fine-tuning/prompting and analyze their ability to abstain from generating low-confidence outputs. Motivated by their failures in self-reflection and over-reliance on heldout sets, we propose two novel approaches that are based on model collaboration, i.e., LLMs probing other LLMs for knowledge gaps, either cooperatively or competitively. Extensive experiments with three LLMs on four QA tasks featuring diverse knowledge domains demonstrate that both cooperative and competitive approaches to unveiling LLM knowledge gaps achieve up to 19.3% improvements on abstain accuracy against the strongest baseline. Further analysis reveals that our abstention methods pinpoint failure cases in retrieval augmentation and knowledge gaps in multi-hop reasoning. 1 Cooperate Question LLM Proposed Answer self others Factual Expert Commonsense Expert Math Expert "Please review the proposed answer and provide feedback on its correctness." Domain Knowledge 1 Feedback 1 Feedback 2 Feedback 3 Feedback 1 LLM 1 Feedback 2 LLM 2 Feedback 3 LLM 3 Judge "Based on the feedback, the proposed answer is: A. True B. False The answer is B. False" "Please propose an alternative answer." Alternative Answer 1 "Generate a knowledge paragraph about <alternative answer>." Alternative Knowledge 1 "Answer the question with the knowledge: feel free to ignore irrelevant or wrong information." Alternative Knowledge 2 Alternative Knowledge 3

For agents

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

get_harvested_code_for_paper("2402.00367")
get_code_for_paper("2402.00367")
have("2402.00367")

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

curl https://syntology.ai/api/ran/2402.00367.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.00367.svg)](https://syntology.ai/paper/2402.00367)

Connect an agent — have() is free.