SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.18167 · 2024

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations

arXiv · PDF · Open in the Atlas

Code that ran

4 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, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 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/2403.18167.json · badge: /api/ran/2403.18167.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
jadeleiyu/lm_hallucination_mechanisms canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
get_key_pos_effects Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jadeleiyu/lm_hallucination_mechanisms/src/hall_mech/cpi.py
pointer only (licence: NONE) · get_code("81bf77133fd70403")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jadeleiyu/lm_hallucination_mechanisms 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.

get_top_pred_ents Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jadeleiyu/lm_hallucination_mechanisms/src/hall_evol/pararel_lm_eval.py
pointer only (licence: NONE) · get_code("199f089770d66ddc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jadeleiyu/lm_hallucination_mechanisms 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.

get_true_obj_ranks Ran
ran, violated the contract we drafted
jadeleiyu/lm_hallucination_mechanisms/src/hall_evol/pararel_lm_eval.py
pointer only (licence: NONE) · get_code("49834773bd1d24db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jadeleiyu/lm_hallucination_mechanisms 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.

untuple Ran
ran, honoured the contract we drafted
jadeleiyu/lm_hallucination_mechanisms/src/hall_mech/cpi.py
pointer only (licence: NONE) · get_code("b0efe66854e42cd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jadeleiyu/lm_hallucination_mechanisms 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.

run_get_noise_and_te Not yet run
unverified (harvested, no recorded run)
jadeleiyu/lm_hallucination_mechanisms/src/hall_mech/cpi.py
pointer only (licence: NONE) · get_code("82f1717a2c29255a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jadeleiyu/lm_hallucination_mechanisms 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, 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 5 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

State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. To explore the mechanistic causes of these hallucinations, we create diagnostic datasets with subject-relation queries and adapt interpretability methods to trace hallucinations through internal model representations. We discover two general and distinct mechanistic causes of hallucinations shared across LMs (Llama-2, Pythia, GPT-J): 1) knowledge enrichment hallucinations: insufficient subject attribute knowledge in lower layer MLPs, and 2) answer extraction hallucinations: failure to select the correct object attribute in upper layer attention heads. We also found these two internal mechanistic causes of hallucinations are reflected in external manifestations. Based on insights from our mechanistic analysis, we propose a novel hallucination mitigation method through targeted restoration of the LM's internal fact recall pipeline, demonstrating superior performance compared to baselines.

For agents

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

get_harvested_code_for_paper("2403.18167")
get_code_for_paper("2403.18167")
have("2403.18167")

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

curl https://syntology.ai/api/ran/2403.18167.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.18167.svg)](https://syntology.ai/paper/2403.18167)

Connect an agent — have() is free.