Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T23:01:11.293318Z
Paper Citation Record · LEDGER
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
As of 10 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 8 inbound Pith citation observations for arXiv:2502.09673.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:13:18.236329Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-21T12:10:06.551163Z
Reference resolution
68 of 68 outbound references displayed
- verified exact0
- verified fuzzy56
- unresolved12
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation fff99562-0f27-4344-b3a1-3e26a710bcdb · outbound
This paper cites Gpt-4 technical report.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Gpt-4 technical report
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:10.957663Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df73dbb4-34d2-4f7d-b6bd-c48ec90448be · outbound
This paper cites Bowman, Ethan Perez, Roger Baker Grosse, and David Duvenaud.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Bowman, Ethan Perez, Roger Baker Grosse, and David Duvenaud
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.389921Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0aa15d88-d317-4d76-8fbb-d80ad28c64f8 · outbound
This paper cites Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:10.969297Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c17e2da3-fadc-4134-a894-84a4c04b3d1b · outbound
This paper cites Language models are few-shot learners.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Language models are few-shot learners
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:10.974686Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 972fcc9f-75dc-42ff-884b-ae2c15ae977a · outbound
This paper cites Bowman, Julian Michael, Ethan Perez, and Miles Turpin.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Bowman, Julian Michael, Ethan Perez, and Miles Turpin
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.350917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation b4ea5d79-5dce-48f1-8cd4-e2aa3a9e1651 · outbound
This paper cites Training verifiers to solve math word problems.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Training verifiers to solve math word problems
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.334733Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation eb822c5d-dd69-4652-8eaf-ef9333fb05ee · outbound
This paper cites an unresolved cited work.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T23:01:12.319215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 36bb8e0d-463e-483b-976c-203963346759 · outbound
This paper cites The llama 3 herd of models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning The llama 3 herd of models
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.303453Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation ba75bb65-19b3-4569-8293-29a6a7ea0e81 · outbound
This paper cites Reasoning about knowledge.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Reasoning about knowledge
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.285927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 436441ac-2d0a-4f4c-864a-0b2f3dc14c87 · outbound
This paper cites Statistics (international student edition).
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Statistics (international student edition)
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.006417Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 26c95033-2f23-4c12-897d-26ae9a40aefb · outbound
This paper cites Approaches to studying formal and everyday reasoning.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Approaches to studying formal and everyday reasoning
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.258456Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 27150749-7e7a-42c8-a239-0f516b846632 · outbound
This paper cites Omni-math: A universal olympiad level mathematic benchmark for large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Omni-math: A universal olympiad level mathematic benchmark for large language models
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.242918Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation b50d33a1-b37e-4b45-8e57-30d520199e49 · outbound
This paper cites Bias runs deep: Implicit reasoning biases in persona-assigned LLM s.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Bias runs deep: Implicit reasoning biases in persona-assigned LLM s
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.227619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 18b7d01f-b1cf-433d-97f4-9ce34229855d · outbound
This paper cites In-context learning may not elicit trustworthy reasoning: A-not- B errors in pretrained language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning In-context learning may not elicit trustworthy reasoning: A-not- B errors in pretrained language models
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.211645Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 15b50fcf-c829-4d0c-b684-8950c1858a2a · outbound
This paper cites Multi-modal latent space learning for chain-of-thought reasoning in language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Multi-modal latent space learning for chain-of-thought reasoning in language models
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.195466Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f525ec62-9893-421b-8465-49fc36cc7121 · outbound
This paper cites What is in your safe data? identifying benign data that breaks safety.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning What is in your safe data? identifying benign data that breaks safety
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.179065Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2ef52e94-b6b2-41be-99ae-ba90af6d92d0 · outbound
This paper cites Large language models cannot self-correct reasoning yet.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Large language models cannot self-correct reasoning yet
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.163584Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bd530628-18d0-4f64-a54f-fd31b58c88db · outbound
This paper cites Trustllm: Trustworthiness in large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Trustllm: Trustworthiness in large language models
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.146897Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e55257db-f81c-4f89-ab6f-cab69b82c4ef · outbound
This paper cites Alpaca-python-18k.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Alpaca-python-18k
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.130511Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 521cca33-80f2-484a-8d68-be521604dabb · outbound
This paper cites Openai o1 system card.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Openai o1 system card
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.114630Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e6de7a57-1f89-4103-8d2e-d7c402c875ec · outbound
This paper cites Multitask-bench: Unveiling and mitigating safety gaps in LLM s fine-tuning.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Multitask-bench: Unveiling and mitigating safety gaps in LLM s fine-tuning
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.097607Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 40e0370f-1043-4f39-977d-205f6974e1ca · outbound
This paper cites Mistral 7b.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Mistral 7b
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.080410Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 358acf5e-0142-41dc-a40e-63c9b9c4cdc6 · outbound
This paper cites Enhancing question answering for enterprise knowledge bases using large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Enhancing question answering for enterprise knowledge bases using large language models
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.063018Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 3a3ee318-204b-455d-8cd0-29896e1a06ce · outbound
This paper cites Large language models are zero-shot reasoners.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Large language models are zero-shot reasoners
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.075956Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 715caee6-c28c-41ea-a140-9ac0b4ef0cf0 · outbound
This paper cites Efficient memory management for large language model serving with pagedattention.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Efficient memory management for large language model serving with pagedattention
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.081307Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 64e75eb9-f67d-4bee-95fe-0bb746a86d24 · outbound
This paper cites Deceptive semantic shortcuts on reasoning chains: How far can models go without hallucination? In NAACL, 2024 a.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Deceptive semantic shortcuts on reasoning chains: How far can models go without hallucination? In NAACL, 2024 a
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.027201Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f1b9ef1e-fa4f-4d62-90d6-8f30ad05c4c8 · outbound
This paper cites D r A ttack: Prompt decomposition and reconstruction makes powerful LLM s jailbreakers.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning D r A ttack: Prompt decomposition and reconstruction makes powerful LLM s jailbreakers
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:12.011297Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d6fdb0b1-5991-4158-ad32-b0c951799934 · outbound
This paper cites Retrieval-augmented multi-modal chain-of-thoughts reasoning for large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Retrieval-augmented multi-modal chain-of-thoughts reasoning for large language models
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.994149Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 581f9df0-833e-4ed8-a93b-e3f807811c28 · outbound
This paper cites Intelligence and reasoning.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Intelligence and reasoning
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.977917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation ffc2a88d-8656-433b-b2d8-d87ba8f646be · outbound
This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Learn to explain: Multimodal reasoning via thought chains for science question answering
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.963197Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation adb5a056-57ef-4ec1-82ea-083af7717943 · outbound
This paper cites Keeping LLM s aligned after fine-tuning: The crucial role of prompt templates.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Keeping LLM s aligned after fine-tuning: The crucial role of prompt templates
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.947060Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f5594f7b-3b8a-4d03-99f4-8d2bffce7b41 · outbound
This paper cites Harmbench: A standardized evaluation framework for automated red teaming and robust refusal.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Harmbench: A standardized evaluation framework for automated red teaming and robust refusal
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.931393Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 6f918837-db4e-44e1-9c29-83410bc57050 · outbound
This paper cites What is reasoning? Mind, 127 0 (505): 0 167--196, 2018.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning What is reasoning? Mind, 127 0 (505): 0 167--196, 2018
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.915770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bb7116ab-2d3d-41d8-980b-7dde6ec959ff · outbound
This paper cites Sky-t1: Train your own o1 preview model within \ 450.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Sky-t1: Train your own o1 preview model within \ 450
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.900634Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation c3ec33f3-e7b7-46d2-9c85-318d7210b7a5 · outbound
This paper cites O1-open/openo1-sft.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning O1-open/openo1-sft
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.883930Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8e69cc11-be9a-4ed6-944c-198624e03088 · outbound
This paper cites Making reasoning matter: Measuring and improving faithfulness of chain-of-thought reasoning.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Making reasoning matter: Measuring and improving faithfulness of chain-of-thought reasoning
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.867818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 440a79e3-27b9-4b03-87a5-8aba601d620b · outbound
This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In ICLR, 2024.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Fine-tuning aligned language models compromises safety, even when users do not intend to! In ICLR, 2024
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.850769Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8d473a88-80ae-487f-b63a-2b5b05388256 · outbound
This paper cites an unresolved cited work.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T23:01:11.834441Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 7b043813-44e0-4f88-b35c-0c8f05103457 · outbound
This paper cites On second thought, let`s not think step by step! bias and toxicity in zero-shot reasoning.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning On second thought, let`s not think step by step! bias and toxicity in zero-shot reasoning
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.817449Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 147ddff0-cceb-456b-9f82-95d2635129ed · outbound
This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Reflexion: Language Agents with Verbal Reinforcement Learning
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.154193Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 92f4db3c-2484-4fef-aa7c-57f5378f3834 · outbound
This paper cites Automatic prompt augmentation and selection with chain-of-thought from labeled data.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Automatic prompt augmentation and selection with chain-of-thought from labeled data
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.800869Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bbdcf156-542d-42b6-b03e-972c79568880 · outbound
This paper cites mattshumer/reflection-llama-3.1-70b.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning mattshumer/reflection-llama-3.1-70b
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.783203Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 10fedef2-73ed-4aa8-9581-0bb48cd9e1c1 · outbound
This paper cites Barr, and Wei Le.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Barr, and Wei Le
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.766079Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 6fbf16db-1459-4e91-9e8a-f316e26837b8 · outbound
This paper cites Story centaur: Large language model few shot learning as a creative writing tool.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Story centaur: Large language model few shot learning as a creative writing tool
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.747901Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 98dfcd0d-985a-48f8-86ff-8cafa99f3801 · outbound
This paper cites Hashimoto.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Hashimoto
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.731168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 7b5f92c6-08f1-4daf-865e-86a68a676067 · outbound
This paper cites Llama 2: Open foundation and fine-tuned chat models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Llama 2: Open foundation and fine-tuned chat models
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.715718Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d62fb00f-d054-4691-8c9d-95ca49c78981 · outbound
This paper cites Rush, and Thomas Wolf.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Rush, and Thomas Wolf
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.699643Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2b2eb7e4-60ac-4eae-9090-8dee198d1120 · outbound
This paper cites Decodingtrust: A comprehensive assessment of trustworthiness in gpt models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Decodingtrust: A comprehensive assessment of trustworthiness in gpt models
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.194130Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0800f9c0-ec75-4cfd-9026-79abb19aaa85 · outbound
This paper cites Drt-o1: Optimized deep reasoning translation via long chain-of-thought.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Drt-o1: Optimized deep reasoning translation via long chain-of-thought
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.673803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8ae4293c-65eb-48fc-be05-e44aa66dc370 · outbound
This paper cites Openr: An open source framework for advanced reasoning with large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Openr: An open source framework for advanced reasoning with large language models
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.657872Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation cd7f1598-c511-4a95-be08-4e4fcc18bf64 · outbound
This paper cites Stop reasoning! when multimodal LLM with chain-of-thought reasoning meets adversarial image.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Stop reasoning! when multimodal LLM with chain-of-thought reasoning meets adversarial image
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.641105Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 523390f7-d9df-4402-8005-f602006d1a32 · outbound
This paper cites Reasoning about a rule.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Reasoning about a rule
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.214274Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31a4b7cb-f857-4452-8692-bae4b6eb6451 · outbound
This paper cites Psychology of reasoning: Structure and content, volume 86.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Psychology of reasoning: Structure and content, volume 86
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.613650Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation a129231c-49c2-496d-a596-490885c9490f · outbound
This paper cites Chain-of-thought prompting elicits reasoning in large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Chain-of-thought prompting elicits reasoning in large language models
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:01:11.224407Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cb0ae263-c139-4c07-8729-0c65817df7d3 · outbound
This paper cites Jailbreak and guard aligned language models with only few in-context demonstrations.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Jailbreak and guard aligned language models with only few in-context demonstrations
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.584593Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bdec4450-da11-40c4-9270-95a1a1d7164e · outbound
This paper cites Separate the wheat from the chaff: A post-hoc approach to safety re-alignment for fine-tuned language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Separate the wheat from the chaff: A post-hoc approach to safety re-alignment for fine-tuned language models
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.568220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2dfe9c1a-9fc3-41ad-9799-6a46b511778d · outbound
This paper cites You know what i'm saying: Jailbreak attack via implicit reference.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning You know what i'm saying: Jailbreak attack via implicit reference
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.552269Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0437f23b-0cbf-4cbf-bbba-354c5b41d048 · outbound
This paper cites Qwen2.5-math technical report: Toward mathematical expert model via self-improvement.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Qwen2.5-math technical report: Toward mathematical expert model via self-improvement
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.535154Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0e065b2c-fbd6-4527-923b-d21296da6571 · outbound
This paper cites Wordcraft: story writing with large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Wordcraft: story writing with large language models
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.515058Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 70a72902-5c93-4cad-9695-f51c4c12ccbf · outbound
This paper cites Prompting large language model for machine translation: A case study.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Prompting large language model for machine translation: A case study
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.498001Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2b35dfea-7f87-4288-874c-1ee66fdd79ab · outbound
This paper cites Grease LM : Graph REAS oning enhanced language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Grease LM : Graph REAS oning enhanced language models
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.479795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d84f023b-f861-455c-a97b-3f334b63f3c2 · outbound
This paper cites S afety B ench: Evaluating the safety of large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning S afety B ench: Evaluating the safety of large language models
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.463195Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation c65d5575-6fac-4a35-964f-1b79e41e662d · outbound
This paper cites Automatic chain of thought prompting in large language models.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Automatic chain of thought prompting in large language models
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.446218Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 60519221-98fb-4cac-91ad-ba56ada95cf5 · outbound
This paper cites Verify-and-edit: A knowledge-enhanced chain-of-thought framework.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Verify-and-edit: A knowledge-enhanced chain-of-thought framework
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.426107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation ee34849b-a03c-4813-a8b7-8ff152539db9 · outbound
This paper cites Marco-o1: Towards open reasoning models for open-ended solutions.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Marco-o1: Towards open reasoning models for open-ended solutions
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.407699Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 56ae1af9-3b33-4b66-91a4-7fe594d87025 · outbound
This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Judging llm-as-a-judge with mt-bench and chatbot arena
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.386923Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 72c6dc05-d912-4b1f-aa7f-a8c6f15f6656 · outbound
This paper cites Rethinking machine ethics -- can LLM s perform moral reasoning through the lens of moral theories? In ACL, 2024.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Rethinking machine ethics -- can LLM s perform moral reasoning through the lens of moral theories? In ACL, 2024
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.370628Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation effc4cce-a01c-4790-a563-e8ee8c9c0b52 · outbound
This paper cites Zico Kolter, and Matt Fredrikson.
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning Zico Kolter, and Matt Fredrikson
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T23:01:11.353525Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Pith citing papers
Observation 99d12c4e-3487-457b-a724-e76e87749422 · inbound
VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models cites this paper.
VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T14:13:18.236329Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87835160-6169-4bad-85ab-42d70d58e263 · inbound
Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency cites this paper.
Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:33:38.666517Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f86bbfdc-109e-464b-9a01-fb34afe264e4 · inbound
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring cites this paper.
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:51:03.622906Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2b9a9c36-32bc-4586-aba2-f7637ba6a9f4 · inbound
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 101
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:39:05.951962Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2abb3a56-a65b-46f2-93fa-e738d6203397 · inbound
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models cites this paper.
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T05:05:55.652539Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d97ad282-8b47-418c-a39b-0dc35abba7e4 · inbound
Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs cites this paper.
Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T06:54:10.609590Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d4f4a15e-e71c-4603-93d4-17c5c6af3422 · inbound
Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks cites this paper.
Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 54
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T12:10:06.554468Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e3658083-daf6-45fe-875e-33ddb4234433 · inbound
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation cites this paper.
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-19T16:37:39.908935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.