Skip to content

Author

V. K. Madisetti

We have 5 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

A Closer Look at Language Model Introspection: Probing Information and Reporting

One way to study language-model introspection is to test whether models can identify where their activations have been perturbed. We train a simple linear classifier to identify the perturbed sentence from the model's activations, then compare its predictions with the model's own answers across pretraining and injectio...

D. Rubin, Vincenzo Timmel, Xu-Feng He et al. · 0 citations
Open access Sep 2026

Programmed Interventions To Prevent Delusions From Excessive Use of Conversational AI Bots

Large language models (LLMs) frequently endorse and elaborate on users’ delusional beliefs, a failure mode termed psychogenicity in the Psychosis-Bench study of Au Yeung et al., whose framing we adopt. We present the first systematic evaluation of whether anti-sycophancy interventions transfer to psychosis-relevant con...

Lorenzo de la Loza, V. K. Madisetti · 0 citations
Open access 2026

Training-Free Cross-Domain Learning Transfer in Reasoning Models

Results demonstrate that explicit structural pattern matching can enable zero-shot cross-domain reasoning transfer without target-domain labels or model-weight updates, and show that the improvement comes from the combination of graph-based abstraction, WL-kernel structural retrieval, and verifier-controlled selective...

Sonali Pandey, V. K. Madisetti · 0 citations

When Too Many Cooks Spoil the Broth: Three Failure Modes of Multi-Agent LLM Reliability

A three-phase framework treating self-confidence assessment, peer-resistance capability, and error correlation as orthogonal axes requiring distinct training signals is proposed, and query-inherent rarity, not shared training, is identified as the dominant driver of correlated failure.

Aradhana Rai, V. K. Madisetti · 0 citations
Open access 2026

ANVIL-FL: Runtime-Aware Fault Localization for Code Generation and Debugging

By combining dynamic runtime signals with structured LLM prompting, this framework demonstrates that failure-proximal runtime context can yield accurate, explainable, and cost-effective method-level fault localization within the BugsInPy setting.

Ahman J. Smith, V. K. Madisetti · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.