Language Model Safety Evaluation

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 58% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 347

All topics

TriBench-Ko: Evaluating LLM Risks in Judicial Workflows
May 5, 2026Haesung Lee, Gyubin Choi, Eun-Ju Lee +5LLM Evaluation Language Model Safety Evaluation
Center for Trustworthy AI, Seoul National University · Graduate School of Data Science, Seoul National University · Responsible AI Team, KT +1
Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
May 5, 2026Haoyu Zhang, Mohammad Zandsalimy, Shanu SushmitaLanguage Model Safety Evaluation Adversarial Attacks on LLMs
† Northeastern University · ‡ Ansys
The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure
May 4, 2026Rahul KumarLanguage Model Safety Evaluation Adversarial Attacks on LLMs
Independent Researcher
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
May 3, 2026Jialin Song, Xiaodong Liu, Weiwei Yang +4LLM Safety Benchmarks Adversarial Prompt Generation
Simon Fraser University · Microsoft Research
Artificial intelligence language technologies in multilingual healthcare: Grand challenges ahead
May 2, 2026Vicent Briva-IglesiasMultilingual Language Model Evaluation Language Model Safety Evaluation
School of Applied Languages and Intercultural Studies (SALIS) · CTTS, ADAPT Centre · Dublin City University
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment
May 1, 2026Tung-Ling Li, Hongliang Liu, Yuhao WuLanguage Model Safety Evaluation Adversarial Attacks on LLMs
Palo Alto Networks
Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives
May 1, 2026Mohammed Abu Baker, Luca Baroni, Dan WilhelmLanguage Model Safety Evaluation Language Model Auditing
Meridian Visiting Researcher Programme.
FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios
May 1, 2026Yutao Hou, Yihan Jiang, Yuhan Xie +5Multilingual Language Model Evaluation Language Model Safety Evaluation
Shanghai University of Finance and Economics · Beihang University · Southern University of Science and Technology +1
BabelSafe: A Policy-Grounded Multilingual Safety Benchmark for LLMs
May 1, 2026Yunhan Zhao, Zhaorun Chen, Xingjun Ma +1LLM Safety Benchmarks Multilingual Language Models
University of Illinois Urbana-Champaign · Fudan University · University of Chicago
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
May 1, 2026Minchan Kwon, Sunghyun Baek, Minseo Kim +3Language Model Safety Evaluation Adversarial Attacks on LLMs
1KAIST · 2Naver AI Lab.
ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?
May 1, 2026Joey Chan, Yikun Han, Jingyuan Chen +8LLM Personalization Language Model Safety Evaluation
University of Illinois Urbana-Champaign · University of Virginia · University of Colorado Anschutz +4
Jailbroken Frontier Models Retain Their Capabilities
Apr 30, 2026Daniel Zhu, Zihan Wang, Xuchan Bao +1Language Model Safety Evaluation Jailbreak Attacks
Anthropic
How Frontier LLMs Adapt to Neurodivergence Context: A Measurement Framework for Surface vs. Structural Change in System-Prompted Responses
Apr 30, 2026Ishan Gupta, Pavlo BuryiLLM Alignment Language Model Safety Evaluation
Harrisburg University of Science and Technology
Characterizing the Consistency of the Emergent Misalignment Persona
Apr 30, 2026Anietta Weckauff, Yuchen Zhang, Maksym AndriushchenkoLanguage Model Safety Evaluation Persona Consistency
ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center
Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype
Apr 30, 2026Matthew Christian AgustinLanguage Model Safety Evaluation LLM Guardrails
Responsible Innovation Lab Tempe, Arizona, USA
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
Apr 29, 2026Mingqian Zheng, Malia Morgan, Liwei Jiang +2LLM Safety Benchmarks Language Model Safety Evaluation
Carnegie Mellon University · Allen Institute for AI · University of Washington
Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
Apr 29, 2026Wenhao Lan, Shan Li, Xinhua Lai +4Adversarial Training Language Model Safety Evaluation
University of Chinese Academy of Sciences, Beijing, China · Inner Mongolia University of Technology, Inner Mongolia, China · Tsinghua University, Beijing, China +1
From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Models
Apr 28, 2026Mengya Hu, Qiong Wei, Sandeep AtluriLanguage Model Safety Evaluation LLM Safety
Responsible AI, Microsoft
Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
Apr 28, 2026Jan Dubiński, Jan Betley, Anna Sztyber-Betley +2Language Model Safety Evaluation Emergent Misalignment in Language Models
1Warsaw University of Technology · 4Truthful AI · University College London +2
Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance
Apr 28, 2026Jon-Paul CacioliLanguage Model Safety Evaluation LLM Safety
Independent Researcher, Melbourne, Australia
Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment
Apr 28, 2026James Pustejovsky, Nikhil KrishnaswamyRL for Language Models Language Model Safety Evaluation
Brandeis University · Waltham, MA, USA · Colorado State University +1
Evaluating whether AI models would sabotage AI safety research
Apr 27, 2026Robert Kirk, Alexandra Souly, Kai Fronsdal +2Language Model Safety Evaluation LLM Auditing
UK AI Security Institute · UK AISI Research Affiliate
How Sensitive Are Safety Benchmarks to Judge Configuration Choices?
Apr 27, 2026Xinran ZhangLLM Safety Benchmarks LLM-as-a-Judge
University of California, Berkeley, Berkeley CA 94720, USA
Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models
Apr 25, 2026Sharan RamjeeLLM Backdoor Attacks Moral Reasoning in Language Models
Stanford University
Semantic Denial of Service in LLM-controlled robots
Apr 25, 2026Jonathan Steinberg, Oren GalLanguage Model Safety Evaluation Adversarial Attacks on LLMs
Swarms & AI Lab (SAIL) · University of Haifa
Estimating Tail Risks in Language Model Output Distributions
Apr 24, 2026Rico Angell, Raghav Singhal, Zachary Horvitz +4Language Model Safety Evaluation Importance Sampling
Center for Data Science, New York University · Department of Computer Science, New York University · Columbia University
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
Apr 23, 2026Tharindu Kumarage, Lisa Bauer, Yao Ma +7Reward Hacking Language Model Safety Evaluation
Amazon Nova Responsible AI
Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
Apr 23, 2026Naheed Rayhan, Sohely JahanLanguage Model Safety Evaluation Adversarial Attacks on LLMs
Jagannath University · University of Barishal
Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles
Apr 22, 2026Irti Haq, Belén SaldíasLanguage Model Safety Evaluation Social Bias in Language Models
University of Washington, USA
Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
Apr 22, 2026Inderjeet Nair, Jie Ruan, Lu WangLLM Alignment Language Model Safety Evaluation
Computer Science and Engineering University of Michigan Ann Arbor, MI 48109, USA

May 5, 2026, cs.CLJ/K move · Enter open · S save

TriBench-Ko: Evaluating LLM Risks in Judicial Workflows

Haesung Lee, Gyubin Choi, Eun-Ju Lee, So-Min Lee+4

Center for Trustworthy AI, Seoul National University · Graduate School of Data Science, Seoul National University · Responsible AI Team, KT+1

LLM Evaluation Language Model Safety Evaluation Language Model Bias Evaluation Language Model Robustness

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar examination performance or classification, which fail to capture the performance and risks inherent in day-to-day judicial processes. To address this, we publicly release TriBench-Ko, a Korean benchmark designed to evaluate potential deployment risks of LLMs within the context of verified judicial task requirements. It covers four core tasks: jurisprudence summarization, precedent retrieval, legal issue extraction, and evidence analysis. It jointly assesses model behavior across multiple deployment risk categories, including inaccuracy (hallucination, omission, statutory misapplication), biases (demographic, overcompliance), inconsistencies (prompt sensitivity, non-determinism), and adjudicative overreach. Each item is structured to systematically assess both task performance and a specific risk type based on real judicial decisions. Our evaluation of a range of contemporary LLMs reveals that many models frequently manifest significant risks, most notably struggling with precedent retrieval and failing to capture critical legal information. We provide a comprehensive diagnosis of these LLMs and pinpoint critical areas where LLM-generated outputs in judicial contexts necessitate rigorous inspection and caution. Our dataset and code are available at https://github.com/holi-lab/TriBench-Ko

Momentum

Related topics

Latest papers 347