SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01548 · 2024

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures 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/2403.01548.json · badge: /api/ran/2403.01548.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-nlp/activation_decoding canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
extract_answer_from_output Ran
ran; our contract draft was wrong, not the code
hkust-nlp/activation_decoding/eval_knowledge_qa.py
pointer only (licence: NONE) · get_code("11575f75b626d3cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-nlp/activation_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.

load_csv Ran
ran; our contract draft was wrong, not the code
hkust-nlp/activation_decoding/eval_tqa.py
pointer only (licence: NONE) · get_code("297c84ffca2864db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-nlp/activation_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.

download_url Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from voidism/DoLa
pointer only; the stored copy get_code serves, from voidism/DoLa, is pointer only (licence: NONE) · get_code("0f14b819bc361c25")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

get_default_conv_template Not yet run
unverified (harvested, no recorded run)
hkust-nlp/activation_decoding/conversation.py
pointer only (licence: NONE) · get_code("529b0ce0a10b8ff6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hkust-nlp/activation_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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 0 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
download_url 6 other papers
3 dated earlier, 3 later
2309.03883 (2023-09)
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
2312.15710 (2023-12)
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
2401.05930 (2024-01)
SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully
and 3 more not named here
extract_answer_from_output 5 other papers
2 dated earlier, 3 later
2309.03883 (2023-09)
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
2401.05930 (2024-01)
SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully
2410.06101 (2024-10)
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
and 2 more not named here
load_csv 2 other papers
2 later
2504.04635 (2025-04)
Steering off Course: Reliability Challenges in Steering Language Models
2509.16598 (2025-09)
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
get_default_conv_template 1 other paper
1 later
2504.04635 (2025-04)
Steering off Course: Reliability Challenges in Steering Language Models

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) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based metric to quantify the ``sharpness'' among the in-context hidden states and incorporate it into the decoding process to formulate a constrained decoding approach. Experiments on various knowledge-seeking and hallucination benchmarks demonstrate our approach's consistent effectiveness, for example, achieving up to an 8.6 point improvement on TruthfulQA. We believe this study can improve our understanding of hallucinations and serve as a practical solution for hallucination mitigation.

For agents

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

get_harvested_code_for_paper("2403.01548")
get_code_for_paper("2403.01548")
have("2403.01548")

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

curl https://syntology.ai/api/ran/2403.01548.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01548.svg)](https://syntology.ai/paper/2403.01548)

Connect an agent — have() is free.