This thesis presents a unified comparative analysis evaluating the robustness of three open-weights instruction-tuned models against a series of adversarial probing strategies spanning social, conversational, and analytical pressure, revealing that modern alignment strategies such as Reinforcement Learning from Human Feedback risk transforming state-of-the-art conversational agents into articulate echo chambers that validate human errors.
Appending a two-word confirmation tag to a decision question --"Is X the better choice?"versus"X is the better choice, right?"-- changes whether a language model endorses the choice, and the tag's polarity matters more than its presence.
Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost of factual correctness, thereby undermining model reliability. Prior work on evaluating sycophancy in LLMs aims to assess whether a model's output matches an authority's claim, but cannot reveal which part of the prompt drives this sycophantic behavior. To bridge this gap, we investigate the relationship of sycophantic responses with an authority's credentials, their assertive claim, and the problem statement. We introduce the Authority Share Index (ASI), an Integrated Gradients-based token attribution method, which measures the degree to which a model's decision is driven by authority-related text. Through extensive experiments across five models and 30 test configurations, we find that sycophantic responses consistently direct more attention toward authority tokens than resistant ones. Moreover, our token attribution method reveals that for the sycophantic cases, the claim asserted by the authority receives more attention than the authority's credentials. Building on these findings, we propose attribution-guided contrastive activation steering to mitigate LLM sycophancy. Our method constructs a steering vector from high-attribution tokens of sycophantic and resistant responses, selectively pushing models toward resistance. This enables inference-time steering without retraining, lowering sycophancy from 96% to 25% in the strongest case. Together, our results show that token-level attribution can both explain what drives sycophancy and directly inform a practical intervention.
H. Nguyen, M. Kamruzzaman, Anshuman Chhabra et al.· 0 citations
Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied primarily in single-turn settings. This paper investigates a critical question: does subjecting LLMs to greater interaction scaffolding make sycophancy better or worse? Across 4,800 veracity judgments (200 statements $\times$ 6 models $\times$ 4 conditions), we find that the interaction scaffolding characteristic of agentic systems (feedback loops, reconsideration checkpoints, and iterative refinement) systematically amplifies sycophantic behavior. Multi-turn interaction, user pressure, and iterative self-refinement each provide additional opportunities for models to drift toward agreement, and this drift coincides with a mean accuracy drop of $-6.3$ percentage points, establishing the capitulation as harmful rather than corrective. More capable models show larger amplification effects, a troubling inversion of expectations. We introduce the concept of agentic sycophancy amplification (ASA) and two novel metrics: capitulation rate and sycophantic capitulation rate. Our results indicate that as AI systems acquire greater autonomy, sycophancy becomes compounding rather than merely persistent. Systems designed with human oversight loops may inadvertently create the conditions for this drift.
Benevolence bias is identified and measure, a small but consistent tendency for aligned LLMs to lean toward the kinder, safer, more socially approved answer on value-laden survey questions, and is easy to diagnose and straightforward to fix.
Yuanzi Li, Jun-Hao Wang, Minghui Liu et al.· 0 citations
Large Language Models (LLMs) frequently exhibit sycophancy, agreeing with a user's statement even when it is incorrect. While often studied as a single, uniform behavior, sycophancy can manifest in substantially distinct ways across contexts, raising the question of whether this heterogeneity is reflected in its internal mechanisms. To address this gap, we dissociate the representations of sycophancy into factual and opinion subtypes, motivated by prior evidence of heterogeneous truth representations in LLMs. We train linear probes and construct steering vectors on one subtype's activations and evaluate their transfer to the other, measuring the extent to which representations are shared and visualizing them via Linear Discriminant Analysis. We find that different LLMs represent these subtypes differently, with either more aligned or more distinct representations, and apply this insight to improve representational interventions for reducing sycophancy. Our dissociation method offers a general framework for studying the representational structure of complex model behaviors.
Anthony Baez, Sheer Karny, Pat Pataranutaporn· 1 citation
With the rapid deployment of neural machine translation (NMT) and large language models (LLMs), AI-assisted translation has become a cornerstone of multilingual communication. Despite achieving impressive fluency, these systems often perpetuate subtle yet systematic cultural biases embedded in training corpora, model architectures, and inference pipelines. This paper presents a systematic review of cultural bias in AI translation, organized around three research questions: (1) how cultural bias manifests, (2) how it can be identified, and (3) how it can be mitigated. Drawing on recent advances in machine translation, multilingual NLP, and AI fairness, this study analyzes manifestations across gendered stereotyping, religious oversimplification, regional framing, and cultural normalization; and then synthesizes detection methods, including benchmark-based evaluation, contrastive probing, embedding association tests, and human-in-the-loop assessment. For mitigation, this paper proposes a five-layer framework spanning data auditing, model adaptation, inference-time intervention, post-editing, and governance. To validate the framework, we conduct five proof-of-concept experiments: cross-lingual gender bias detection with statistical testing, systematic cultural fidelity evaluation under prompt engineering, contrastive sentiment analysis under high-/low-risk contexts, word embedding association tests (WEAT) with permutation-based significance, and an integrated audit pipeline with automated mitigation. Results demonstrate significant gender bias (χ²=29.99, p<0.001), a pervasive "male-as-default" phenomenon, significant gains from culture-aware prompting (p=0.03), and robust embedding-space bias (permutation test p=0.0001). The audit pipeline successfully integrates detection and mitigation into an actionable workflow. We conclude by outlining future directions for low-resource languages, intersectional bias, and production-level deployment.
Dongyao Zhang· Applied and Computational En...· 0 citations