Pith. sign in

Paper Citation Record · LEDGER

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity

As of 9 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2509.11141.

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

pith.paper-citation-record.v1
2509.11141 v1

Coverage vector

measured 60 of 60 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:09:25.440403Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

60 of 60 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved60
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ae0a3f32-d0c1-4a42-bbaa-83cd76fb38ed · outbound

This paper cites , " * write output.state after.block = add.period write newline.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity , " * write output.state after.block = add.period write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.464392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.464392Z digest=sha256:6c25be27260420e396bfecc308ad024145333ebd0227e282f91ae72ff2d7ea80

Observation 954843d8-4b82-4f41-bad1-ac7fe6c2eb1f · outbound

This paper cites write newline.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity write newline

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.523114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.523114Z digest=sha256:ece09bff794ba612291209127b54889fc27427e8d6c97931f1f81435c8c2769d

Observation 8839b49c-4b95-4fe2-9488-8ed005733b1a · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.590973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.590973Z digest=sha256:d5b9e8aafd58060850483b15d29afc2b187bcd051b218d96849b7a13b044819b

Observation 5c016285-d37f-4cf7-b0c5-0c6ee3313ae9 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.663770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.663770Z digest=sha256:4c9902a39e71ff008279e39988792837105f59c5e25266acd40eb7d4d1899f7b

Observation bc7de08c-7e5b-46f7-a953-e916330a7d46 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.715202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.715202Z digest=sha256:c2bf68fb8c929e6a659ae22f020d7e815a10728370733bd4b3a17cb2b5e61e95

Observation f7722ca6-eea3-4c2a-bf3d-07285c9d544e · outbound

This paper cites J.; and Wong, E.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity J.; and Wong, E

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.792027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.792027Z digest=sha256:1e3e53785af82fbbd011cfca1dc6b95898f26140164b06bb6b6e94825506a4eb

Observation a2a80b6d-7af5-4f77-8ed3-576f4bb55b13 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.849271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.849271Z digest=sha256:6bccb14903e1e8a37d01e95bd3de8e6836ec0ad67fb63ff9ded671f942d3d14f

Observation 4ff98936-0ccb-48a2-a0d0-a004404507b5 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:21.928047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:21.928047Z digest=sha256:5d03eaeb62ae3a350124ab9141dfbdfedb870c06a38571ab0885540f01dcae3b

Observation 0646dde3-2559-4907-a15f-a3e9fe1993ed · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.011239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.011239Z digest=sha256:5d9664ec98abae47407857123280df3265dd77a990bdd87dd29b776ceda981c3

Observation 974d005c-7b7f-4674-a9ce-d1ba58489373 · outbound

This paper cites J.; and Bing, L.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity J.; and Bing, L

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.068545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.068545Z digest=sha256:9408abbc5943d512cd54dc2ba565ebccb5b5743220d69ade34c1c4fb15fced6f

Observation 26a0eb27-fb5e-4514-87ff-807b749f03fe · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.178771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.178771Z digest=sha256:5064658ab4ed4ed601b21b50a4d5247598da7f7bbfb23c0aeb8cc3a9ed9ab69a

Observation 9c45c5bf-c384-4f87-a7e4-fa7af98a7757 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.237113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.237113Z digest=sha256:f67b51acc989bdf00d134752dcbd853ef13172ffc07963fd2ffabca2ede8d19e

Observation 5dfe6192-93ee-48ff-bf5a-68490a941b4e · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.322997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.322997Z digest=sha256:f87d60b7bec057f0bda7ca9aff203ff125d977f2ee64a313b4f8d9f2b8406334

Observation a3aa8610-e902-4a5b-a853-ddf0737c8541 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.396334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.396334Z digest=sha256:7437b20f733df2826e94820e0196b7c80e89a0738716c3dc8718baec477f335d

Observation e64fc346-1801-4b80-825f-c8052ba9aaeb · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.446949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.446949Z digest=sha256:450d7a9d704998b2541aaa4d265254d931676b28edf2454094aba15fa2b922a9

Observation 2057c88f-ab0c-4338-b2d2-19b67116d14c · outbound

This paper cites C.; Li, M.; Tay, L.; and Ungar, L.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity C.; Li, M.; Tay, L.; and Ungar, L

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.502577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.502577Z digest=sha256:cc980bf3659191c685a6f7ce5515c563365d0f3b4f8d5cabc9d2ef8a4fd7db86

Observation bb9d86c9-e5d2-42bb-b6db-f42c4688ceb6 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.583232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.583232Z digest=sha256:7343c53ac24920eef05296999552993b5379bb771b3bf3c9d9f00b74110dc0db

Observation 8eb38931-7a71-4cb8-bc87-e83f0f58b84f · outbound

This paper cites Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.668034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.668034Z digest=sha256:323b3d043a8c7f4d4441910aad4953e50296ef019ae81bc48ff160c54b4bcb80

Observation d9024f78-5def-4c21-a74c-a1fa6cf2bbcf · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.722925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.722925Z digest=sha256:303c45003b8f8883634a418d345039afe373a3b797902a098b74356037c8c900

Observation d899ed46-e8aa-432d-8f4b-37286dd340fb · outbound

This paper cites The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.815334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.815334Z digest=sha256:40fffe3bfc715f9bdaca3f2779276cbe6727b6e455f180a3de8f522ba1b25335

Observation 0f5c067b-bf53-435b-973d-6a8cf525e7b4 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:22.941949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:22.941949Z digest=sha256:018eaaa8d01920bd2e237e9e42c01e881913c5beb4104e94c994b658daddc7c2

Observation 66f592a7-a041-480a-9439-29bc9fef0d18 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.015769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.015769Z digest=sha256:282f0cfe1824ebc52413a743092601113c1170b799794d40d6d62e180051e5e4

Observation 4f14f09e-a88b-4b92-8cbe-f689aebbdaa5 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.101338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.101338Z digest=sha256:41fa0d236142f968109fe831ded114fca988234717a72a4f35a421563ac2745b

Observation 91d4abac-a5e4-4992-807e-3409da154da2 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.125655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.125655Z digest=sha256:cee15274922fbcbef4ccc0e77f8cc95ccc0b02a7fd5f7121a8a62d356248c3ce

Observation c1c8ef81-b4dc-43f0-963d-62b3df05f757 · outbound

This paper cites K.; Romero, P.; and Stachl, C.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity K.; Romero, P.; and Stachl, C

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.129701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.129701Z digest=sha256:acf0ec27ad542e2a084e3edce5068b5a95093dbc463329f8055010ceaff80901

Observation df175b0b-dac6-45c6-8f08-04d18a22901f · outbound

This paper cites A Cross-Language Investigation into Jailbreak Attacks in Large Language Models.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.133866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.133866Z digest=sha256:bee5957801ebe76286accee2553e6810c8e4d11a6fdccf858cc7b79e1e91988a

Observation 0eb7d02e-2494-4bd7-8777-32abb484d7f4 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.138351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.138351Z digest=sha256:317a4b78f0441e419cbaa3f80de8767b5ee8a6696e49a5fcc7884468b6bc9c21

Observation f9dd53e9-69eb-4fd6-bfec-5aaec82f6090 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.142408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.142408Z digest=sha256:94405c2453770321aed085dbdddaa1c65860992ffe12d2b320c049d7b1500ef0

Observation 91e831dc-af45-4b83-9d7c-f820c4bc7964 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.146687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.146687Z digest=sha256:45d6f3eb8b5edeaafcf11fba34960a38b4fa148f4538371457dc1230a24a6764

Observation f4f23a8b-c6f8-4686-af48-30d74261e68e · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.150917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.150917Z digest=sha256:d638114d8153330640a1925a0f41baaeb36f8210d1084c813cf7371ceeed6f64

Observation c4d93268-5af2-4710-9efd-0466b10710e5 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.154912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.154912Z digest=sha256:594904354e8fb54fa32e745030d396e8f23df24531648df51a91298aabc2885e

Observation 2bf90759-5ef9-4f6b-ae6f-61e3e1bdde52 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.158624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.158624Z digest=sha256:51b16bf4f0794f720330a7b6d0f19b56d6c73ae904db40aa248e4e136898b19a

Observation ce6f6a29-24a0-4239-83d9-dbbd0f252074 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.163567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.163567Z digest=sha256:52ddff53db235f4f3c85bfec90cac326bdcab050739038365f5cb17210364da5

Observation d690e3a1-83fe-4f23-92ac-cd08f42bcf4d · outbound

This paper cites S.; Singer, Y.; and Karbasi, A.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity S.; Singer, Y.; and Karbasi, A

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.167620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.167620Z digest=sha256:49a35c6b7ab67e5ad031ba495eba15b1b0152519fcc191e2790c7695ae340016

Observation 6e0cc636-715b-4b38-9fcd-a3b066f028b3 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.171328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.171328Z digest=sha256:65fce2329a95407a1de80f85ef546c6deef80a1500717fad525f660d39c133f7

Observation 8db05beb-119b-4e45-943d-1f177399a996 · outbound

This paper cites Emojinal Intelligence.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Emojinal Intelligence

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.175312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.175312Z digest=sha256:f9168f8d8bc8b622fd2e4a22c0c03794c2d435ebb504a275cd7f809656a631de

Observation 1e551003-aa9c-45e8-89bb-dc1cac103f68 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.179356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.179356Z digest=sha256:bfcc66abc7c7da93cb6ff62ede3038defedb47824a2ab906a52e1c17c4a628f5

Observation 653cede4-2f1d-4c9e-9886-bbcb11828e3c · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.183242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.183242Z digest=sha256:9b241708053ffa564dee82a0b8dd299446ac2f76d1dba90ef4be00d24d549c42

Observation 29e5d1cc-11db-41b4-8462-59d1cf0c9e38 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.186954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.186954Z digest=sha256:744ff59f13d633b07e4db13bdff0c5e07f715f2d4a6b2c1cdecf3239ead92465

Observation 8797d32b-913b-4603-bbc8-7f9817beb7cf · outbound

This paper cites EmojiLM: Modeling the New Emoji Language.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity EmojiLM: Modeling the New Emoji Language

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.190724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.190724Z digest=sha256:28fd74853d3be0cdd8a5777084b598c551a5397ec612b9a3c89f9baa8d77d12d

Observation 81912842-ef26-4aa1-a46b-e84239d2287e · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.195119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.195119Z digest=sha256:8ae894b0c697629dede5cec7f88df29c347e0b78d2dbf9509eabe0e906450104

Observation 0505ac26-09e6-419d-bfa8-df482125ac85 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.199006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.199006Z digest=sha256:42fce6aaeb253ca000f2e737cdb8fef5a622d1ed087c5709f27016b97d5261e7

Observation 07874e8d-2d48-4efd-bbbc-17ca8dccaff9 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.202838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.202838Z digest=sha256:e75de219ca9ff65c793460149bd208ca5db06faad192ebd277afec72f1528a7e

Observation 1200d523-5e82-4e51-8695-34e9e076a5f5 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.206984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.206984Z digest=sha256:5931858535340dba25aaa2085267fbf6fadee41406866c177a295fe2fe603010

Observation b7a47e21-d602-4f9c-bb5e-ad6ae56f3639 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.215026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.215026Z digest=sha256:df94c23ebf00314bd3ec42bc75315f4625161fd259a75149ca39d9c6e4ba13d8

Observation 93116b57-ddb2-42cf-bb5a-4d8139daee91 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.279444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.279444Z digest=sha256:d54d8bc067bddf6d3070e930355d3a11b1b7e43bcdfa6e509ae724354a3d1501

Observation 9e43712a-2c4f-40fc-b81c-abf327c7d8e4 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.395854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.395854Z digest=sha256:44ae3540756749435caad8ea0b601a428331b4fee0f26eb22e6f9f6c2ce9ff86

Observation 044ee81b-4c92-404c-84db-405df5d2fb9f · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.517073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.517073Z digest=sha256:33d0a52528842d17c5842e4cf5ea3d361c3f3a50c29ee5d35cf9024d7ffbc703

Observation 4fa55ea7-07a3-40b5-be26-620a90360682 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.631307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.631307Z digest=sha256:d71e0e744e619c6b2251d03eac741ada3d8c8d76aa10fd776d17cf2b4c5feceb

Observation 529b6262-f6ad-47d8-84d4-fe067be09f1c · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.756401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.756401Z digest=sha256:874f9805cf22f14e48b1429583d2d5f12aa1b6bb14f3f89a2a3147a7b9889b20

Observation 07d91fc3-1402-4d81-8f1a-d5f472f99269 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.875652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.875652Z digest=sha256:76a61e6a770447bb067f904c89e3ef64d24bcd49ba9b2163d4f09a6485c2983b

Observation 70002513-9738-4a17-85d7-0abe22dc40c6 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:23.949401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:23.949401Z digest=sha256:bfe76eaf7b6075ba2b55d9c52239146eab60e6e6d9d9311baa91b6e705535add

Observation 025aa74b-1660-4307-8b6b-fdcdd71f72e4 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:24.077060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:24.077060Z digest=sha256:f9a0515eb4c83c6d46d51f34c3da76f140d676e88e0dae9f0ab62167470534ec

Observation 14e021f4-b94e-4ddc-addd-d14cec6975ed · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:24.212002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:24.212002Z digest=sha256:991c3f640e5b8a5e8b941f3aafa5fd12ccee6f226bda3ae287f7172775145e3d

Observation 5df767ad-c2d8-45fd-b0c0-091880179e56 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:24.405820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:24.405820Z digest=sha256:69e8f8203f1aaed9bc1f77a450e46a45e54594aa58cb294d0671cbef72417472

Observation e61b9fcd-0245-46fd-82b4-0964d3fc863d · outbound

This paper cites Irony in Emojis: A Comparative Study of Human and LLM Interpretation.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Irony in Emojis: A Comparative Study of Human and LLM Interpretation

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:24.603063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:24.603063Z digest=sha256:1dd48ec4340e8a19bbf8deec8a393a2e20811adc4374f1b4f10abb85e3492cac

Observation 74f49128-bdab-4da5-bb14-871cd7d4038c · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:24.797227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:24.797227Z digest=sha256:f682dc01e8f2a7ffd4050b501dd533a7d4902760880e0ddf2cb06056f4a36720

Observation 8e3a1e74-08a1-463f-8c27-e8ec1ebc79c5 · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:25.003810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:25.003810Z digest=sha256:a3cf4b406f27eae030499041c6f462c2e051d7b1e1889fd55fc72f57ab4bda22

Observation 25f616ed-1bcb-4960-8885-f0c3932004f9 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:25.250360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:25.250360Z digest=sha256:450a553440a0161d5a89df7e879f96cf083cd2a64d4bfe7b6bb52df62725bb42

Observation 625d4b61-e822-430b-a589-036add20f9aa · outbound

This paper cites an unresolved cited work.

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity Unresolved cited work

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-04T17:09:25.440403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T17:09:25.440403Z digest=sha256:77926679f1000ff88a3063ec49f6187f2c0d338c06130cfc51eb9afe95dcb612

Pith citing papers

No inbound Pith citation observations are available.