arXiv subjects

Sunishchal Dev

Publications and source records attributed to Sunishchal Dev.

At least 19 recordsLinked to original sources

arXiv2026

How Language Models Choose Sides: Internal Representations of Instruction Hierarchy

We study how instruction-tuned LLMs arbitrate direct conflicts between system and user instructions. We introduce a benchmark of 41 paired constraints with deterministic verifiers and evaluate eight models under matched baseline, conflict, and same-channel control conditions. Behaviourally, the models split into three regimes by System Authority Delta: hierarchy-respecting models use the system channel as an authority signal, anti-hierarchy models follow the system less often than their same-channel baseline predicts, and no-effect models show little channel sensitivity. Llama-3.1-8B is the strongest anti-hierarchy case in our suite, following the system in only 0.10 of conflict trials. We use this behavioural failure case to ask whether user-preferring arbitration reflects the absence of an internal conflictresolution signal. It does not: on Llama-3.1-8B, the conflict outcome is linearly decodable from residual-stream activations at 0.97 balanced accuracy, 17 percentage points above a metadata-only baseline, with analogous signals on Qwen2.5-7B and gpt-oss-20b. Steering with a layer-12 mean of four per-conflict logistic-regression directions raises genuine system compliance from 0.132 to 0.530, while directions selected mainly for pooled separability steer poorly. User-preferring conflict resolution can therefore coexist with a readable internal arbitration signal, and successful intervention depends on the geometry of the readout rather than probe accuracy alone

cs.AI↗

arXiv2026

Open Weight AI Models Require Proportional Evaluation Approaches

Open-weight AI models (OWMs), or models released with publicly-available weights, are distributing rapidly and approaching the performance levels of leading closed-weight AI models (CWMs). While OWMs offer substantial scientific and economic benefits, their release introduces distinct risk factors for which existing evaluation practices, largely designed for CWM deployment, fail to account. In this paper, we argue that these risk factors demand distinct proportional evaluation (PE) approaches: evaluating without system-level safeguards (PE1), assessing robustness to modifications that undo model-level safeguards (PE2), testing selective capability amplification (PE3), and proxying worst-case misuse (PE4). We systematically review current evaluation practices of OWMs released in 2025 through April 2026, finding that only one of the 37 families of models reviewed fulfills PE1-4 and most do not fulfill any. This paper targets policymakers, funders, and researchers involved in AI evaluation. As OWMs grow increasingly capable, their evaluation warrants close attention from developers, funders, and governance bodies alike.

cs.CY↗

arXiv2026

CA-BED: Conversation-Aware Bayesian Experimental Design

Large Language Models (LLMs) excel at static reasoning tasks, yet their performance often degrades in interactive scenarios where information must be actively acquired through questioning. A key challenge lies in selecting questions that reduce uncertainty while incorporating responses that may be ambiguous or only partially informative. To address this, we propose Conversation-Aware Bayesian Experimental Design (CA-BED), an inference-time probabilistic dialog planning framework that integrates Bayesian Experimental Design with LLM-based likelihood estimation to optimize question selection over multiple conversational turns. CA-BED maintains a belief distribution over hypotheses, anticipates possible answers, and propagates expected information gain through a simulated conversation tree. Across two structured entity-deduction benchmarks, CA-BED yields an average 21.8% improvement in success rates over direct prompting, with comparable gains relative to alternative information-seeking methods. It achieves these gains with an average increase of only 1.8 conversational turns compared to direct prompting.

cs.CL↗

arXiv2026

Judge Reliability Harness: Stress Testing the Reliability of LLM Judges

We present the Judge Reliability Harness, an open source library for constructing validation suites that test the reliability of LLM judges. As LLM based scoring is widely deployed in AI benchmarks, more tooling is needed to efficiently assess the reliability of these methods. Given a benchmark dataset and an LLM judge configuration, the harness generates reliability tests that evaluate both binary judgment accuracy and ordinal grading performance for free-response and agentic task formats. We evaluate four state-of-the-art judges across four benchmarks spanning safety, persuasion, misuse, and agentic behavior, and find meaningful variation in performance across models and perturbation types, highlighting opportunities to improve the robustness of LLM judges. No judge that we evaluated is uniformly reliable across benchmarks using our harness. For example, our preliminary experiments on judges revealed consistency issues as measured by accuracy in judging another LLM's ability to complete a task due to simple text formatting changes, paraphrasing, changes in verbosity, and flipping the ground truth label in LLM-produced responses. The code for this tool is available at: https://github.com/RANDCorporation/judge-reliability-harness

cs.AI↗

arXiv2026

The science and practice of proportionality in AI risk evaluations

A global challenge in artificial intelligence (AI) regulation lies in achieving effective risk management without compromising innovation and technical progress. The European Union (EU) Artificial Intelligence Act represents the first regulatory attempt worldwide to navigate this tension in the form of a binding, risk-based framework. In August 2025, obligations for providers of general-purpose AI (GPAI) models under the EU AI Act entered into application. They require providers of the most advanced GPAI models to evaluate possible systemic risks stemming from their models. This raises the regulatory challenge of ensuring that the evaluations provide meaningful risk information without imposing excessive burden on providers. The principle of proportionality, a binding requirement under EU law, requires the regulator to calibrate its actions to their intended objectives. The application of proportionality to model evaluations for AI risk opens opportunities to develop scientific methods that operationalize such calibration within concrete evaluation practices.

cs.CY↗

arXiv2026

Broken Chains: The Cost of Incomplete Reasoning in LLMs

Reasoning-specialized models like OpenAI's 5.1 and DeepSeek-V3.2 allocate substantial inference compute to extended chain-of-thought (CoT) traces, yet reasoning tokens incur significant costs. How do different reasoning modalities of code, natural language, hybrid, or none do perform under token constraints? We introduce a framework that constrains models to reason exclusively through code, comments, both, or neither, then systematically ablates token budgets to 10\%, 30\%, 50\%, and 70\% of optimal. We evaluate four frontier models (GPT-5.1, Gemini 3 Flash, DeepSeek-V3.2, Grok 4.1) across mathematical benchmarks (AIME, GSM8K, HMMT). Our findings reveal: (1) \textbf{truncated reasoning can hurt} as DeepSeek-V3.2 achieves 53\% with no reasoning but only 17\% with truncated CoT at 50\% budget; (2) \textbf{code degrades gracefully} as Gemini's comments collapse to 0\% while code maintains 43-47\%; (3) \textbf{hybrid reasoning underperforms} single modalities; (4) \textbf{robustness is model-dependent} as Grok maintains 80-90\% at 30\% budget where OpenAI and DeepSeek collapse to 7-27\%. These results suggest incomplete reasoning chains actively mislead models, with implications for deploying reasoning-specialized systems under resource constraints.

cs.LG↗

arXiv2026

Seven simple steps for log analysis in AI systems

AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess whether an evaluation worked as intended. Researchers have started developing methods for log analysis, but a standardised approach is still missing. Here we suggest a pipeline based on current best practices. We illustrate it with concrete code examples in the Inspect Scout library, provide detailed guidance on each step, and highlight common pitfalls. Our framework provides researchers with a foundation for rigorous and reproducible log analysis.

cs.AI↗

arXiv2026

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark evaluating 11 prompting paradigms across four LLM families. Using ETHICS, Scruples, WildJailbreak, and our new robustness test, ETHICS-Contrast, we measure performance via our proposed Unified Moral Safety Score (UMSS), a metric balancing accuracy and safety. Our results show that compact, exemplar-guided scaffolds outperform complex multi-stage reasoning, providing higher UMSS scores and greater robustness at a lower token cost. While multi-turn reasoning proves fragile under perturbations, few-shot exemplars consistently enhance moral stability and jailbreak resistance. ProMoral-Bench establishes a standardized framework for principled, cost-effective prompt engineering.

cs.AI↗

arXiv2026

A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that identifies and updates only the neurons most responsible for a given behavior, a targeted approach that allows for fine-tuning with significantly less data. Using sparse autoencoders (SAEs) and linear probes, we isolate the 3% of MLP neurons most predictive of a target behavior, decode them into residual space, and fine-tune only those neurons using gradient masking. We demonstrate this approach on the task of reducing sycophantic behavior, where our method matches or exceeds state-of-the-art performance on four benchmarks (Syco-Bench, NLP, POLI, PHIL) using Gemma-2-2B and 9B models. Our results show that sparse, neuron-level updates offer a scalable and precise alternative to full-model fine-tuning, remaining effective even in situations when little data is available

cs.LG↗

arXiv2026

Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering

Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study this phenomenon systematically, we introduce FalseCite, a curated dataset designed to capture and benchmark hallucinated responses induced by misleading or fabricated citations. Running GPT-4o-mini, Falcon-7B, and Mistral 7-B through FalseCite, we observed a noticeable increase in hallucination activity for false claims with deceptive citations, especially in GPT-4o-mini. Using the responses from FalseCite, we can also analyze the internal states of hallucinating models, visualizing and clustering the hidden state vectors. From this analysis, we noticed that the hidden state vectors, regardless of hallucination or non-hallucination, tend to trace out a distinct horn-like shape. Our work underscores FalseCite's potential as a foundation for evaluating and mitigating hallucinations in future LLM research.

cs.CL↗

arXiv2025

Emergent Persuasion: Will LLMs Persuade Without Being Prompted?

With the wide-scale adoption of conversational AI systems, AI are now able to exert unprecedented influence on human opinion and beliefs. Recent work has shown that many Large Language Models (LLMs) comply with requests to persuade users into harmful beliefs or actions when prompted and that model persuasiveness increases with model scale. However, this prior work looked at persuasion from the threat model of $\textit{misuse}$ (i.e., a bad actor asking an LLM to persuade). In this paper, we instead aim to answer the following question: Under what circumstances would models persuade $\textit{without being explicitly prompted}$, which would shape how concerned we should be about such emergent persuasion risks. To achieve this, we study unprompted persuasion under two scenarios: (i) when the model is steered (through internal activation steering) along persona traits, and (ii) when the model is supervised-finetuned (SFT) to exhibit the same traits. We showed that steering towards traits, both related to persuasion and unrelated, does not reliably increase models' tendency to persuade unprompted, however, SFT does. Moreover, SFT on general persuasion datasets containing solely benign topics admits a model that has a higher propensity to persuade on controversial and harmful topics--showing that emergent harmful persuasion can arise and should be studied further.

cs.AI↗

arXiv2025

Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs

We introduce Contrastive Region Masking (CRM), a training free diagnostic that reveals how multimodal large language models (MLLMs) depend on specific visual regions at each step of chain-of-thought (CoT) reasoning. Unlike prior approaches limited to final answers or attention maps, CRM provides causal, step-level attribution by systematically masking annotated regions and contrasting the resulting reasoning traces with unmasked baselines. Applied to datasets such as VisArgs, CRM reveals distinct failure modes: some models preserve reasoning structure, but hallucinate when evidence is missing, while others ground tightly to visual cues yet collapse under perturbations. By shifting the evaluation from correctness of answers to faithfulness of reasoning, CRM reframes visual benchmarks as diagnostic tools, highlighting the need for multimodal evaluation frameworks that measure not just performance, but also robustness and fidelity of reasoning.

cs.LG↗

arXiv2025

Sumudu Neural Operator for ODEs and PDEs

We introduce the Sumudu Neural Operator (SNO), a neural operator rooted in the properties of the Sumudu Transform. We leverage the relationship between the polynomial expansions of transform pairs to decompose the input space as coefficients, which are then transformed into the Sumudu Space, where the neural operator is parameterized. We evaluate the operator in ODEs (Duffing Oscillator, Lorenz System, and Driven Pendulum) and PDEs (Euler-Bernoulli Beam, Burger's Equation, Diffusion, Diffusion-Reaction, and Brusselator). SNO achieves superior performance to FNO on PDEs and demonstrates competitive accuracy with LNO on several PDE tasks, including the lowest error on the Euler-Bernoulli Beam and Diffusion Equation. Additionally, we apply zero-shot super-resolution to the PDE tasks to observe the model's capability of obtaining higher quality data from low-quality samples. These preliminary findings suggest promise for the Sumudu Transform as a neural operator design, particularly for certain classes of PDEs.

cs.LG↗

arXiv2025

Modeling and Predicting Multi-Turn Answer Instability in Large Language Models

As large language models (LLMs) are adopted in an increasingly wide range of applications, user-model interactions have grown in both frequency and scale. Consequently, research has focused on evaluating the robustness of LLMs, an essential quality for real-world tasks. In this paper, we employ simple multi-turn follow-up prompts to evaluate models' answer changes, model accuracy dynamics across turns with Markov chains, and examine whether linear probes can predict these changes. Our results show significant vulnerabilities in LLM robustness: a simple "Think again" prompt led to an approximate 10% accuracy drop for Gemini 1.5 Flash over nine turns, while combining this prompt with a semantically equivalent reworded question caused a 7.5% drop for Claude 3.5 Haiku. Additionally, we find that model accuracy across turns can be effectively modeled using Markov chains, enabling the prediction of accuracy probabilities over time. This allows for estimation of the model's stationary (long-run) accuracy, which we find to be on average approximately 8% lower than its first-turn accuracy for Gemini 1.5 Flash. Our results from a model's hidden states also reveal evidence that linear probes can help predict future answer changes. Together, these results establish stationary accuracy as a principled robustness metric for interactive settings and expose the fragility of models under repeated questioning. Addressing this instability will be essential for deploying LLMs in high-stakes and interactive settings where consistent reasoning is as important as initial accuracy.

cs.CL↗

arXiv2025

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought

As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak private information through their internal reasoning processes, violating contextual privacy expectations. These leaky thoughts occur when models inadvertently expose sensitive details in their reasoning traces, even when final outputs appear safe. The challenge lies in preventing such leakage without compromising the model's reasoning capabilities, requiring a delicate balance between privacy and utility. We introduce Steering Activations towards Leakage-free Thinking (SALT), a lightweight test-time intervention that mitigates privacy leakage in model's Chain of Thought (CoT) by injecting targeted steering vectors into hidden state. We identify the high-leakage layers responsible for this behavior. Through experiments across multiple LLMs, we demonstrate that SALT achieves reductions including $18.2\%$ reduction in CPL on QwQ-32B, $17.9\%$ reduction in CPL on Llama-3.1-8B, and $31.2\%$ reduction in CPL on Deepseek in contextual privacy leakage dataset AirGapAgent-R while maintaining comparable task performance and utility. Our work establishes SALT as a practical approach for test-time privacy protection in reasoning-capable language models, offering a path toward safer deployment of LLM-based personal agents.

cs.CR↗

arXiv2025

Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computational cost by fully generating all branches. Self-Truncation Best-of-N (ST-BoN) mitigates this by truncating unpromising paths early, but its reliance on consistency-based heuristics is a limitation as it does not directly evaluate branch quality. We present KL-Adjusted Pruned Path Algorithm (KAPPA), an inference-time method that combines Kullback-Leibler divergence, confidence, and entropy into a principled scoring function to guide progressive pruning. By promoting diversity during exploration and selectively eliminating low-scoring branches, KAPPA maintains accuracy while substantially reducing memory and token usage. Experiments on GSM8K and MATH500 with DeepSeek-R1-Distill-Qwen-1.5B and Qwen2.5-7B-Instruct demonstrate that KAPPA stabilizes performance in smaller models and achieves up to ~60% reduction in peak memory and ~90% reduction in total token generation relative to BoN, with minimal impact on accuracy.

cs.LG↗

arXiv2025

DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code

The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors, predominantly utilizing zero-shot methods, such as Fast DetectGPT or GPTZero, either incur high computational cost or lack sufficient accuracy, often with a trade-off between the two, leaving room for further improvement. To address these gaps, we propose the fine-tuning of encoder-only Small Language Models (SLMs), in particular, the pre-trained models of RoBERTA and CodeBERTa using specialized datasets on source code and other natural language to prove that for the task of binary classification, SLMs outperform LLMs by a huge margin whilst using a fraction of compute. Our encoders achieve AUROC $= 0.97$ to $0.99$ and macro-F1 $0.89$ to $0.94$ while reducing latency by $8$-$12\times$ and peak VRAM by $3$-$5\times$ at $512$-token inputs. Under cross-generator shifts and adversarial transformations (paraphrase, back-translation; code formatting/renaming), performance retains $\geq 92%$ of clean AUROC. We release training and evaluation scripts with seeds and configs; a reproducibility checklist is also included.

cs.CL↗

arXiv2025

AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI

Goal changes are a defining feature of real world multi-turn interactions, yet current agent benchmarks primarily evaluate static objectives or one-shot tool use. We introduce AgentChangeBench, a benchmark explicitly designed to measure how tool augmented language model agents adapt to mid dialogue goal shifts across three enterprise domains. Our framework formalizes evaluation through four complementary metrics: Task Success Rate (TSR) for effectiveness, Tool Use Efficiency (TUE) for reliability, Tool Call Redundancy Rate (TCRR) for wasted effort, and Goal-Shift Recovery Time (GSRT) for adaptation latency. AgentChangeBench comprises 2,835 task sequences and five user personas, each designed to trigger realistic shift points in ongoing workflows. Using this setup, we evaluate several frontier models and uncover sharp contrasts obscured by traditional $\text{pass}@k$ scores: for example, GPT-4o reaches $92.2\%$ recovery on airline booking shifts while Gemini collapses to $48.6\%$, and retail tasks show near perfect parameter validity yet redundancy rates above $80\%$, revealing major inefficiencies. These findings demonstrate that high raw accuracy does not imply robustness under dynamic goals, and that explicit measurement of recovery time and redundancy is essential. AgentChangeBench establishes a reproducible testbed for diagnosing and improving agent resilience in realistic enterprise settings.

cs.AI↗