arXiv subjects

Darpan Aswal

Publications and source records attributed to Darpan Aswal.

4 recordsLinked to original sources

arXiv2026

Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models

Latent reasoning models (LRMs) replace explicit chain-of-thought with continuous thoughts. Recent work treats observable latent-state patterns, such as BFS-like frontiers and decodable arithmetic computation, as evidence for internal reasoning mechanisms. Evaluating two LRMs (Coconut and CODI) against controls lacking the proposed recurrence or curriculum, we find these patterns also appear in the controls and do not always causally affect behavior. Causal interventions reveal that latent-thought utilization is not binary but graded, scaling with a thought's causal effect on model behavior. Geometric analyses reveal this effect concentrates in low-rank directions whose step-to-step geometry grows more structured as their behavioral influence increases. Latent thoughts should therefore be treated as hidden computation, not hidden explanation: decodability, attention, or static structure alone cannot establish mechanism. LRM interpretability thus requires matched controls and causal tests.

cs.CL↗

arXiv2025

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts

Large Language Models have found success in a variety of applications. However, their safety remains a concern due to the existence of various jailbreaking methods. Despite significant efforts, alignment and safety fine-tuning only provide a certain degree of robustness against jailbreak attacks that covertly mislead LLMs towards the generation of harmful content. This leaves them prone to a range of vulnerabilities, including targeted misuse and accidental user profiling. This work introduces \textbf{ConceptGuard}, a novel framework that leverages Sparse Autoencoders (SAEs) to identify interpretable concepts within LLM internals associated with different jailbreak themes. By extracting semantically meaningful internal representations, ConceptGuard enables building robust safety guardrails -- offering fully explainable and generalizable defenses without sacrificing model capabilities or requiring further fine-tuning. Leveraging advances in the mechanistic interpretability of LLMs, our approach provides evidence for a shared activation geometry for jailbreak attacks in the representation space, a potential foundation for designing more interpretable and generalizable safeguards against attackers.

cs.CL↗

arXiv2025

Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs

Safety-aligned LLMs remain vulnerable to digital phenomena like textese that introduce non-canonical perturbations to words but preserve the phonetics. We introduce CMP-RT (code-mixed phonetic perturbations for red-teaming), a novel diagnostic probe that pinpoints tokenization as the root cause of this vulnerability. A mechanistic analysis reveals that phonetic perturbations fragment safety-critical tokens into benign sub-words, suppressing their attribution scores while preserving prompt interpretability -- causing safety mechanisms to fail despite excellent input understanding. We demonstrate that this vulnerability evades standard defenses, persists across modalities and state-of-the-art (SOTA) models including Gemini-3-Pro, and scales through simple supervised fine-tuning (SFT). Furthermore, layer-wise probing shows perturbed and canonical input representations align up to a critical layer depth; enforcing output equivalence robustly recovers the lost representations, providing causal evidence for a structural gap between pre-training and alignment, and establishing tokenization as a critical, under-examined vulnerability in current safety pipelines.

cs.CL↗

arXiv2025

Efficient Environmental Claim Detection with Hyperbolic Graph Neural Networks

Transformer based models, especially large language models (LLMs) dominate the field of NLP with their mass adoption in tasks such as text generation, summarization and fake news detection. These models offer ease of deployment and reliability for most applications, however, they require significant amounts of computational power for training as well as inference. This poses challenges in their adoption in resource-constrained applications, especially in the open-source community where compute availability is usually scarce. This work proposes a graph-based approach for Environmental Claim Detection, exploring Graph Neural Networks (GNNs) and Hyperbolic Graph Neural Networks (HGNNs) as lightweight yet effective alternatives to transformer-based models. Re-framing the task as a graph classification problem, we transform claim sentences into dependency parsing graphs, utilizing a combination of word2vec \& learnable part-of-speech (POS) tag embeddings for the node features and encoding syntactic dependencies in the edge relations. Our results show that our graph-based models, particularly HGNNs in the poincar\'e space (P-HGNNs), achieve performance superior to the state-of-the-art on environmental claim detection while using up to \textbf{30x fewer parameters}. We also demonstrate that HGNNs benefit vastly from explicitly modeling data in hierarchical (tree-like) structures, enabling them to significantly improve over their euclidean counterparts.

cs.CL↗