CVE-2026-80104 (GCVE-0-2026-80104)
Vulnerability from cvelistv5 – Published: 2026-08-25 20:18 – Updated: 2026-08-29 11:48
VLAI
EPSS
VEX
Title
DB-GPT 0.8.0 Path Traversal Arbitrary File Write via Skill Upload Filename
Summary
DB-GPT builds the destination path for an uploaded skill from the multipart filename without constraining it to the upload directory. skill_upload in packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py takes file.filename as given and writes the request body to upload_dir / filename. A path composed with that operator discards the left operand when the right one is absolute and follows parent references otherwise, so a filename such as ../../../tmp/x or /tmp/x resolves outside the intended directory; nothing canonicalises the result, checks that it remains under the upload root, or prevents a .py suffix. The route's only dependency is get_user_from_headers in dbgpt_serve/utils/auth.py, which returns a request carrying the admin role whether or not a user_id header is supplied, so the endpoint is reachable without credentials. A remote attacker holding no account can therefore write attacker-controlled bytes to any path the server process can write, place a new Python module inside the application package or replace one the application already imports, and obtain code execution in the server process when that module is next imported.
Severity
9.8 (Critical)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-28 22:36 UTC
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
5 references
| URL | Tags |
|---|---|
| https://github.com/eosphoros-ai/DB-GPT | product |
| https://github.com/eosphoros-ai/DB-GPT/blob/v0.8.… | technical-description |
| https://github.com/eosphoros-ai/DB-GPT/releases/t… | release-notes |
| https://pypi.org/project/dbgpt-app/ | product |
| https://www.vulncheck.com/advisories/db-gpt-0.8.0… | third-party-advisory |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| eosphoros-ai | DB-GPT |
Affected:
0.8.0 , < 0.8.1
(semver)
cpe:2.3:a:dbgpt:db-gpt:*:*:*:*:*:*:*:* |
Date Public
2026-08-25 00:00
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-80104",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-28T22:36:32.611124Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-28T22:36:49.668Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"collectionURL": "https://github.com/eosphoros-ai/DB-GPT",
"defaultStatus": "unaffected",
"packageURL": "pkg:pypi/dbgpt-app",
"product": "DB-GPT",
"repo": "https://github.com/eosphoros-ai/DB-GPT",
"vendor": "eosphoros-ai",
"versions": [
{
"lessThan": "0.8.1",
"status": "affected",
"version": "0.8.0",
"versionType": "semver"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:dbgpt:db-gpt:*:*:*:*:*:*:*:*",
"versionEndExcluding": "0.8.1",
"versionStartIncluding": "0.8.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Abhinav Jaswal"
}
],
"datePublic": "2026-08-25T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "DB-GPT builds the destination path for an uploaded skill from the multipart filename without constraining it to the upload directory. skill_upload in packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py takes file.filename as given and writes the request body to upload_dir / filename. A path composed with that operator discards the left operand when the right one is absolute and follows parent references otherwise, so a filename such as ../../../tmp/x or /tmp/x resolves outside the intended directory; nothing canonicalises the result, checks that it remains under the upload root, or prevents a .py suffix. The route\u0027s only dependency is get_user_from_headers in dbgpt_serve/utils/auth.py, which returns a request carrying the admin role whether or not a user_id header is supplied, so the endpoint is reachable without credentials. A remote attacker holding no account can therefore write attacker-controlled bytes to any path the server process can write, place a new Python module inside the application package or replace one the application already imports, and obtain code execution in the server process when that module is next imported."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-29T11:48:02.709Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"tags": [
"product"
],
"url": "https://github.com/eosphoros-ai/DB-GPT"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/eosphoros-ai/DB-GPT/blob/v0.8.0/packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py"
},
{
"name": "DB-GPT v0.8.1 Release Notes",
"tags": [
"release-notes"
],
"url": "https://github.com/eosphoros-ai/DB-GPT/releases/tag/v0.8.1"
},
{
"tags": [
"product"
],
"url": "https://pypi.org/project/dbgpt-app/"
},
{
"name": "VulnCheck Advisory: DB-GPT 0.8.0 Path Traversal Arbitrary File Write via Skill Upload Filename",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/db-gpt-0.8.0-path-traversal-arbitrary-file-write-via-skill-upload-filename"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "DB-GPT 0.8.0 Path Traversal Arbitrary File Write via Skill Upload Filename",
"x_generator": {
"engine": "vulncheck-endgame"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-80104",
"datePublished": "2026-08-25T20:18:35.843Z",
"dateReserved": "2026-08-25T19:35:42.640Z",
"dateUpdated": "2026-08-29T11:48:02.709Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-80104",
"date": "2026-08-31",
"epss": "0.00713",
"percentile": "0.51122"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-80104\",\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"published\":\"2026-08-25T21:18:24.163\",\"lastModified\":\"2026-08-28T23:17:12.590\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"DB-GPT builds the destination path for an uploaded skill from the multipart filename without constraining it to the upload directory. skill_upload in packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py takes file.filename as given and writes the request body to upload_dir / filename. A path composed with that operator discards the left operand when the right one is absolute and follows parent references otherwise, so a filename such as ../../../tmp/x or /tmp/x resolves outside the intended directory; nothing canonicalises the result, checks that it remains under the upload root, or prevents a .py suffix. The route\u0027s only dependency is get_user_from_headers in dbgpt_serve/utils/auth.py, which returns a request carrying the admin role whether or not a user_id header is supplied, so the endpoint is reachable without credentials. A remote attacker holding no account can therefore write attacker-controlled bytes to any path the server process can write, place a new Python module inside the application package or replace one the application already imports, and obtain code execution in the server process when that module is next imported.\"}],\"affected\":[{\"source\":\"disclosure@vulncheck.com\",\"affectedData\":[{\"vendor\":\"eosphoros-ai\",\"product\":\"DB-GPT\",\"defaultStatus\":\"unaffected\",\"collectionURL\":\"https://github.com/eosphoros-ai/DB-GPT\",\"repo\":\"https://github.com/eosphoros-ai/DB-GPT\",\"packageURL\":\"pkg:pypi/dbgpt-app\",\"versions\":[{\"version\":\"0.8.0\",\"lessThan\":\"0.8.1\",\"versionType\":\"semver\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X\",\"baseScore\":9.3,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"vulnConfidentialityImpact\":\"HIGH\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"HIGH\",\"subConfidentialityImpact\":\"NONE\",\"subIntegrityImpact\":\"NONE\",\"subAvailabilityImpact\":\"NONE\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}],\"cvssMetricV31\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-08-28T22:36:32.611124Z\",\"id\":\"CVE-2026-80104\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"yes\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-22\"}]}],\"references\":[{\"url\":\"https://github.com/eosphoros-ai/DB-GPT\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/eosphoros-ai/DB-GPT/blob/v0.8.0/packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/eosphoros-ai/DB-GPT/releases/tag/v0.8.1\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://pypi.org/project/dbgpt-app/\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.vulncheck.com/advisories/db-gpt-0.8.0-path-traversal-arbitrary-file-write-via-skill-upload-filename\",\"source\":\"disclosure@vulncheck.com\"}]}}",
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-80104\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-28T22:36:32.611124Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-28T22:36:46.139Z\"}}], \"cna\": {\"title\": \"DB-GPT 0.8.0 Path Traversal Arbitrary File Write via Skill Upload Filename\", \"source\": {\"discovery\": \"UNKNOWN\"}, \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Abhinav Jaswal\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"Safety\": \"NOT_DEFINED\", \"version\": \"4.0\", \"Recovery\": \"NOT_DEFINED\", \"baseScore\": 9.3, \"Automatable\": \"NOT_DEFINED\", \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"valueDensity\": \"NOT_DEFINED\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N\", \"exploitMaturity\": \"NOT_DEFINED\", \"providerUrgency\": \"NOT_DEFINED\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\", \"vulnerabilityResponseEffort\": \"NOT_DEFINED\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 9.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}], \"affected\": [{\"repo\": \"https://github.com/eosphoros-ai/DB-GPT\", \"vendor\": \"eosphoros-ai\", \"product\": \"DB-GPT\", \"versions\": [{\"status\": \"affected\", \"version\": \"0.8.0\", \"lessThan\": \"0.8.1\", \"versionType\": \"semver\"}], \"packageURL\": \"pkg:pypi/dbgpt-app\", \"collectionURL\": \"https://github.com/eosphoros-ai/DB-GPT\", \"defaultStatus\": \"unaffected\"}], \"datePublic\": \"2026-08-25T00:00:00.000Z\", \"references\": [{\"url\": \"https://github.com/eosphoros-ai/DB-GPT\", \"tags\": [\"product\"]}, {\"url\": \"https://github.com/eosphoros-ai/DB-GPT/blob/v0.8.0/packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/eosphoros-ai/DB-GPT/releases/tag/v0.8.1\", \"name\": \"DB-GPT v0.8.1 Release Notes\", \"tags\": [\"release-notes\"]}, {\"url\": \"https://pypi.org/project/dbgpt-app/\", \"tags\": [\"product\"]}, {\"url\": \"https://www.vulncheck.com/advisories/db-gpt-0.8.0-path-traversal-arbitrary-file-write-via-skill-upload-filename\", \"name\": \"VulnCheck Advisory: DB-GPT 0.8.0 Path Traversal Arbitrary File Write via Skill Upload Filename\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck-endgame\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"DB-GPT builds the destination path for an uploaded skill from the multipart filename without constraining it to the upload directory. skill_upload in packages/dbgpt-app/src/dbgpt_app/openapi/api_v1/agentic_data_api.py takes file.filename as given and writes the request body to upload_dir / filename. A path composed with that operator discards the left operand when the right one is absolute and follows parent references otherwise, so a filename such as ../../../tmp/x or /tmp/x resolves outside the intended directory; nothing canonicalises the result, checks that it remains under the upload root, or prevents a .py suffix. The route\u0027s only dependency is get_user_from_headers in dbgpt_serve/utils/auth.py, which returns a request carrying the admin role whether or not a user_id header is supplied, so the endpoint is reachable without credentials. A remote attacker holding no account can therefore write attacker-controlled bytes to any path the server process can write, place a new Python module inside the application package or replace one the application already imports, and obtain code execution in the server process when that module is next imported.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-22\", \"description\": \"Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)\"}]}], \"cpeApplicability\": [{\"nodes\": [{\"negate\": false, \"cpeMatch\": [{\"criteria\": \"cpe:2.3:a:dbgpt:db-gpt:*:*:*:*:*:*:*:*\", \"vulnerable\": true, \"versionEndExcluding\": \"0.8.1\", \"versionStartIncluding\": \"0.8.0\"}], \"operator\": \"OR\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-08-29T11:48:02.709Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-80104\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-29T11:48:02.709Z\", \"dateReserved\": \"2026-08-25T19:35:42.640Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-08-25T20:18:35.843Z\", \"assignerShortName\": \"VulnCheck\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Loading…
Loading…