Browse State-of-the-Art › Safety Alignment › Papers, page 2
Safety Alignment
Papers archive 2025-07-28
archive papers tagged: 288 · with a code link: 134 · where Syntology ran a sample: 73 (59 with a run with no instrument failure, 14 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (73 of 288 tagged: 59 with a run with no instrument failure, 14 where every run was a failure of Syntology's instrument)
Page 2 of 3: papers 101 to 200 of 288, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. Abstracts are on each paper's page.
-
17 Jun 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)
-
17 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
17 Jun 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
17 Jun 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)
-
10 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (of 7 harvested samples)
-
9 Jun 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
31 May 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
29 May 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
28 May 2024 1 repository listed
-
27 May 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified (of 17 harvested samples)
-
13 May 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
25 Apr 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
18 Apr 2024 1 repository listed Syntology official (archive's flag): 1 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples) · 5 pointer-only (licence)
-
11 Apr 2024 1 repository listed
-
8 Apr 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
28 Feb 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples)
-
25 Feb 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 7 harvested samples)
-
22 Feb 2024 1 repository listed
-
21 Feb 2024 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples) · 11 pointer-only (licence)
-
19 Feb 2024 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples)
-
19 Feb 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
14 Feb 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 6 harvested samples)
-
3 Feb 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
5 Jan 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
12 Dec 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
15 Nov 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
15 Nov 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
25 Oct 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
5 Oct 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
2 Oct 2023 1 repository listed
-
2 Oct 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
12 Aug 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
10 Jul 2023 1 repository listed
-
TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data8 Jul 2025 0 repositories listed
-
Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message7 Jul 2025 0 repositories listed
-
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning6 Jul 2025 0 repositories listed
-
Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks23 Jun 2025 0 repositories listed
-
SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification20 Jun 2025 0 repositories listed
-
Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning17 Jun 2025 0 repositories listed
-
SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression15 Jun 2025 0 repositories listed
-
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring11 Jun 2025 0 repositories listed
-
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)10 Jun 2025 0 repositories listed
-
Refusal-Feature-guided Teacher for Safe Finetuning via Data Filtering and Alignment Distillation9 Jun 2025 0 repositories listed
-
From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment7 Jun 2025 0 repositories listed
-
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets5 Jun 2025 0 repositories listed
-
4 Jun 2025 0 repositories listed Syntology 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models2 Jun 2025 0 repositories listed
-
Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap30 May 2025 0 repositories listed
-
29 May 2025 0 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?29 May 2025 0 repositories listed
-
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack28 May 2025 0 repositories listed
-
PoisonSwarm: Universal Harmful Information Synthesis via Model Crowdsourcing27 May 2025 0 repositories listed
-
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge27 May 2025 0 repositories listed
-
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models26 May 2025 0 repositories listed
-
SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety26 May 2025 0 repositories listed
-
24 May 2025 0 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 1 pointer-only (licence)
-
Safety Alignment via Constrained Knowledge Unlearning24 May 2025 0 repositories listed
-
Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey23 May 2025 0 repositories listed
-
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary23 May 2025 0 repositories listed
-
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning22 May 2025 0 repositories listed
-
"Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs20 May 2025 0 repositories listed
-
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment20 May 2025 0 repositories listed
-
sudoLLM : On Multi-role Alignment of Language Models20 May 2025 0 repositories listed
-
Safety Alignment Can Be Not Superficial With Explicit Safety Signals19 May 2025 0 repositories listed
-
17 May 2025 0 repositories listed Syntology 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples) · 2 pointer-only (licence)
-
SafeVid: Toward Safety Aligned Video Large Multimodal Models17 May 2025 0 repositories listed
-
CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs16 May 2025 0 repositories listed
-
Noise Injection Systemically Degrades Large Language Model Safety Guardrails16 May 2025 0 repositories listed
-
Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data15 May 2025 0 repositories listed
-
FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning12 May 2025 0 repositories listed
-
One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models12 May 2025 0 repositories listed
-
NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models29 Apr 2025 0 repositories listed
-
What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift28 Apr 2025 0 repositories listed
-
AI Awareness25 Apr 2025 0 repositories listed
-
aiXamine: Simplified LLM Safety and Security21 Apr 2025 0 repositories listed
-
Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization19 Apr 2025 0 repositories listed
-
Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models18 Apr 2025 0 repositories listed
-
VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization17 Apr 2025 0 repositories listed
-
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents15 Apr 2025 0 repositories listed
-
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?14 Apr 2025 0 repositories listed
-
LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models14 Apr 2025 0 repositories listed
-
RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability14 Apr 2025 0 repositories listed
-
SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models9 Apr 2025 0 repositories listed
-
ERPO: Advancing Safety Alignment via Ex-Ante Reasoning Preference Optimization3 Apr 2025 0 repositories listed
-
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment3 Apr 2025 0 repositories listed
-
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data2 Apr 2025 0 repositories listed
-
Effectively Controlling Reasoning Models through Thinking Intervention31 Mar 2025 0 repositories listed
-
Safe RLHF-V: Safe Reinforcement Learning from Human Feedback in Multimodal Large Language Models22 Mar 2025 0 repositories listed
-
Align in Depth: Defending Jailbreak Attacks via Progressive Answer Detoxification14 Mar 2025 0 repositories listed
-
Representation-based Reward Modeling for Efficient Safety Alignment of Large Language Model13 Mar 2025 0 repositories listed
-
JBFuzz: Jailbreaking LLMs Efficiently and Effectively Using Fuzzing12 Mar 2025 0 repositories listed
-
Backtracking for Safety11 Mar 2025 0 repositories listed
-
Utilizing Jailbreak Probability to Attack and Safeguard Multimodal LLMs10 Mar 2025 0 repositories listed
-
SafeArena: Evaluating the Safety of Autonomous Web Agents6 Mar 2025 0 repositories listed
-
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety6 Mar 2025 0 repositories listed
-
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning5 Mar 2025 0 repositories listed
-
LLM-Safety Evaluations Lack Robustness4 Mar 2025 0 repositories listed
Syntology lines on 35 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.