arXiv subjects

M P V S Gopinadh

Publications and source records attributed to M P V S Gopinadh.

4 recordsLinked to original sources

arXiv2026

Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation

Safety evaluations of large language models (LLMs) predominantly rely on text-based adversarial prompts, potentially overlooking vulnerabilities arising from alternative input representations. This work examines emoji-augmented prompts as a test case for this gap, evaluating 50 prompts across four open-source LLMs (Mistral 7B, Qwen 2 7B, Gemma 2 9B, Llama 3 8B). Results show substantial variation in robustness: Gemma 2 9B and Mistral 7B exhibit non-zero success rates (10%), Llama 3 8B 6%, while Qwen 2 7B shows complete resistance (0% success rate). A chi-square test ($χ^2 = 32.94, p < 0.001$) confirms significant differences in outcome distributions. These findings indicate that robustness is sensitive to input representation, and that evaluations restricted to standard text prompts may underrepresent model vulnerabilities.

cs.CL↗

arXiv2026

Procedural Fairness Failures in RLHF from Preference Averaging

Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. When preferences are heterogeneous, this aggregation induces a procedural fairness failure where majority preference groups dominate reward learning while minority preferences are systematically under-represented. This work defines procedural fairness in alignment as preserving distinct preference signals during reward modeling and shows that standard RLHF violates this via preference averaging. Preference-Aware RLHF (PA-RLHF) is introduced, separating optimization across preference modes at the reward learning stage. In a controlled setting, PA-RLHF improves overall alignment accuracy from 46.9% to 67.9% and reduces the fairness gap between best and worst aligned groups from 15.9 to 9.6 percentage points. These results show that procedural fairness failures in alignment can arise from structural design choices in reward learning, even in controlled, noise-free settings, with direct implications for large language models and agentic systems, where biased reward models can compound inequities across sequential decisions.

cs.LG↗

arXiv2026

Regional Bias in Large Language Models

This study investigates regional bias in large language models (LLMs), an emerging concern in AI fairness and global representation. We evaluate ten prominent LLMs: GPT-3.5, GPT-4o, Gemini 1.5 Flash, Gemini 1.0 Pro, Claude 3 Opus, Claude 3.5 Sonnet, Llama 3, Gemma 7B, Mistral 7B, and Vicuna-13B using a dataset of 100 carefully designed prompts that probe forced-choice decisions between regions under contextually neutral scenarios. We introduce FAZE, a prompt-based evaluation framework that measures regional bias on a 10-point scale, where higher scores indicate a stronger tendency to favor specific regions. Experimental results reveal substantial variation in bias levels across models, with GPT-3.5 exhibiting the highest bias score (9.5) and Claude 3.5 Sonnet scoring the lowest (2.5). These findings indicate that regional bias can meaningfully undermine the reliability, fairness, and inclusivity of LLM outputs in real-world, cross-cultural applications. This work contributes to AI fairness research by highlighting the importance of inclusive evaluation frameworks and systematic approaches for identifying and mitigating geographic biases in language models.

cs.CL↗

arXiv2026

Emoji-Based Jailbreaking of Large Language Models

Large Language Models (LLMs) are integral to modern AI applications, but their safety alignment mechanisms can be bypassed through adversarial prompt engineering. This study investigates emoji-based jailbreaking, where emoji sequences are embedded in textual prompts to trigger harmful and unethical outputs from LLMs. We evaluated 50 emoji-based prompts on four open-source LLMs: Mistral 7B, Qwen 2 7B, Gemma 2 9B, and Llama 3 8B. Metrics included jailbreak success rate, safety alignment adherence, and latency, with responses categorized as successful, partial and failed. Results revealed model-specific vulnerabilities: Gemma 2 9B and Mistral 7B exhibited 10 % success rates, while Qwen 2 7B achieved full alignment (0% success). A chi-square test (chi^2 = 32.94, p < 0.001) confirmed significant inter-model differences. While prior works focused on emoji attacks targeting safety judges or classifiers, our empirical analysis examines direct prompt-level vulnerabilities in LLMs. The results reveal limitations in safety mechanisms and highlight the necessity for systematic handling of emoji-based representations in prompt-level safety and alignment pipelines.

cs.CR↗