Paper Citation Record · LEDGER

Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 24 inbound Pith citation observations for arXiv:2406.08660.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2406.08660 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:38:27.084069Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T13:09:50.186682Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation c824b213-f103-4f7a-9d58-6b83adcc9506 · inbound

Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning cites this paper.

Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:38:27.084069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4723f1a-2ff4-45ba-9f82-9b0b64c86bd1 · inbound

Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification cites this paper.

Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:10:29.827699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e649f4de-0931-4edc-99ba-0728f7217b19 · inbound

ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing cites this paper.

ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:28:31.636900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef545a3d-8016-42a3-a8d6-2df424f9d74c · inbound

Evaluating Apple Intelligence's Writing Tools for Privacy Against Large Language Model-Based Inference Attacks: Insights from Early Datasets cites this paper.

Evaluating Apple Intelligence's Writing Tools for Privacy Against Large Language Model-Based Inference Attacks: Insights from Early Datasets Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:56:26.799225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a998495-832c-4d28-a230-4b190695278e · inbound

Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models? cites this paper.

Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models? Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:48:14.059947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b792fe22-393d-4e95-be40-20f82e08db06 · inbound

DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media cites this paper.

DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:11:50.088904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb91e4c7-8411-4ac5-835a-883620bb1bd3 · inbound

A Scalable and Efficient Signal Integration System for Job Matching cites this paper.

A Scalable and Efficient Signal Integration System for Job Matching Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T17:50:52.961975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01e10c1a-239c-4664-93e5-8287b7f0de17 · inbound

Few-Shot Vision-Language Reasoning for Satellite Imagery via Verifiable Rewards cites this paper.

Few-Shot Vision-Language Reasoning for Satellite Imagery via Verifiable Rewards Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T12:29:37.121892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd1fb217-0aaf-46eb-b263-f8c95ddbabe7 · inbound

How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting cites this paper.

How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T15:23:18.210440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a408ab3-3988-4c20-a384-57459e10bf20 · inbound

A Multi-Stage Large Language Model Framework for Extracting Suicide-Related Social Determinants of Health cites this paper.

A Multi-Stage Large Language Model Framework for Extracting Suicide-Related Social Determinants of Health Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T23:42:37.750033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2abeab2-fb3c-48a2-a018-9e93252f1051 · inbound

Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning cites this paper.

Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T14:59:49.753715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7287a75c-c8e9-4580-96dc-c925a00895aa · inbound

Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement cites this paper.

Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:33:49.108541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 782d82be-bdb3-4431-8451-5157803b467e · inbound

PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification cites this paper.

PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T21:41:34.476176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36bd8681-e34e-4510-accc-5391a27105c8 · inbound

DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain cites this paper.

DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T20:50:58.634121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1571143d-ae40-476e-8d63-71d3432e34e9 · inbound

Just Use XML: Revisiting Joint Translation and Label Projection cites this paper.

Just Use XML: Revisiting Joint Translation and Label Projection Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T11:45:32.747185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1ef8a843-2f42-48e7-ae53-ef254ed81f88 · inbound

RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models cites this paper.

RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 120

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T11:35:19.242642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8a395793-b26e-4d6c-b9a1-54d7c905d7de · inbound

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents cites this paper.

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:41:26.734590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8955588d-db17-4055-b80c-7a8ccdfc41fb · inbound

Short-form Text Rewriting with Phi Silica cites this paper.

Short-form Text Rewriting with Phi Silica Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:22:34.272664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4bc75b3c-e545-42d7-926f-cc5de63cb6a4 · inbound

Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification cites this paper.

Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 163

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:27:14.939030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4fbcd820-e129-40da-b8db-5acc332fdc00 · inbound

AnnotateThis: Analyzing a human-LLM system for annotating social media data with the concept of climate change mitigation pessimism cites this paper.

AnnotateThis: Analyzing a human-LLM system for annotating social media data with the concept of climate change mitigation pessimism Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-03T03:57:38.266425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aea4ea28-65f1-41fc-8b35-74c8d7d54799 · inbound

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training cites this paper.

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T09:07:48.151677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f5a12b58-7854-4538-8360-b9b69ee7bdb0 · inbound

Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News cites this paper.

Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:09:50.188356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8006d7c3-5a33-4fca-a4a7-f586ded80ca1 · inbound

Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments cites this paper.

Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 69

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:28:18.338085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 398bee97-97ec-42a5-9690-5f13098207e2 · inbound

AIx4Soccer: A Unified Platform Architecture for Football Club Management and Structured Athlete Development cites this paper.

AIx4Soccer: A Unified Platform Architecture for Football Club Management and Structured Athlete Development Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-31T04:29:09.255885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.