arXiv subjects

Tanmoy Chakraborty

Publications and source records attributed to Tanmoy Chakraborty.

At least 19 recordsLinked to original sources

arXiv2026

Swimming versus Screening: How Activity Reshapes the Ionic Cloud of a Charged Particle

A major question in active matter is how interactions between particles are modified by activity. Here, we address this question for Coulomb interactions by considering a charged swimmer immersed in an electrolyte. A static charge is screened by an ionic cloud that decays over the Debye length $λ_D$. We show that the persistent motion of the swimmer can qualitatively modify the steady-state ionic charge-density profile. At low activity, the swimmer appears effectively quasistatic to the ions, and conventional Debye-Hückel screening is recovered. At higher activity, the ballistic-to-diffusive dynamics of the swimmer are reflected in distinct spatial regimes. A power-law decay is followed by a stretched-exponential decay at intermediate distances. At sufficiently large distances, exponential screening is restored, but with an increased screening length, $λ>λ_D$, revealing activity-induced underscreening. Thus, active motion modifies both the spatial form and the range of electrostatic screening. Our results motivate the study of active electrolytes composed of positively and negatively charged swimmers.

cond-mat.stat-mech↗

arXiv2026

High Resolution Hyperspectral Quantum Infrared Imaging with Undetected Photons

Quantum sensing in the infrared regime often demands the use of expensive and cryogenically operated detectors. Nonlinear interferometry has paved the way for information transfer from the infrared to the near--infrared or visible regime in various quantum technologies. A particularly interesting application of these interferometers involves spectrally--resolved quantum imaging using undetected photons, enabled by the use of temperature--tunable parametric amplifiers. In this work, we demonstrate spectrally resolved transmission imaging with undetected photons around 1550 nm using a spontaneous parametric down conversion based folded nonlinear interferometric scheme, registering the attenuation of a zebrafish larva as a biological feasibility test. We characterize and calibrate the interferometer, having achieved spectrally resolved interference fringes with a maximum baseline visibility of $\sim 74\%$ in the near--infrared regime. Phase--stepped readout of a grating spectrometer gives a resolving power of $\sim1460$ (from the spectrometer's point spread function) at 1550 nm, and $\sim 730$ from the coherence length, the finest reported for imaging with undetected photons, over an instantaneous spectral window of $\approx 51$ cm$^{-1}$.

quant-ph↗

arXiv2026

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay

Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection of neuroscience and machine learning. Most brain-encoding studies focus on aligning artificial models with brain activity during language comprehension or passive visual processing, while interactive brain alignment studies have to date been largely limited to reinforcement-learning (RL) agents and theory-based models. To address this gap, we study brain alignment of representative models from two foundation-model types, namely vision-language models (VLMs) and large-action models (LAMs), using fMRI recordings from participants playing naturalistic Atari-style video games. Specifically, we examine how action-focused and reasoning-focused prompts shape the models' internal representations and their alignment with fMRI brain activity. First, we find that both VLMs and LAMs achieve significantly higher voxel-wise encoding performance than RL baselines, with the advantage holding even under matched feature dimensionality. Second, compared to a no-prompt baseline, prompt-driven gains are larger in higher-order frontal-parietal and motor-planning regions than in early visual cortex, roughly 2-2.5$\times$ when averaged over region-of-interest (ROI) groups, although individual regions are heterogeneous. Third, variance partitioning reveals a qualitatively different representational organization. VLM representations are prompt-symmetric (12.4% unique action vs. 9.5% unique reasoning), whereas LAM representations are action-dominant (25.6% unique action vs.-8.2% unique reasoning), with the asymmetry strongest in frontal-motor cortex. Together, these results associate action specialization with distinct cortical alignment patterns in multimodal game-state representations, revealing differences hidden by similar prediction accuracy.

q-bio.NC↗

arXiv2026

Latent Performance Profiling of Large Language Models

Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs on leaderboards faces persistent issues such as data contamination, a narrow task scope, and poor alignment with real-world reliability. Benchmark-based evaluations such as MMLU-Pro, BBH, or IFEval primarily capture \textit{what} a model outputs on fixed test sets, not \textit{how} it processes information, calibrates uncertainty, or structures internal knowledge. In this article, we advocate for a shift from benchmark-centric evaluation toward a complementary, \textit{state-centered intrinsic assessment} of LLMs. To this end, we introduce \textbf{Latent Performance Profiling (LPP)} --- a framework that derives task-agnostic diagnostics from hidden activations and output distributions. LPP defines a set of scalar metrics on a model's latent representations and dynamics, revealing traits that enable interpretable comparisons and uncover hidden vulnerabilities. Unlike static accuracy scores, LPP provides stable, architecture-sensitive signatures across models of similar size. With extensive empirical analyses across eight LLMs, spanning a size range of 0.5B-14B, we demonstrate that models with similar benchmark scores can exhibit contrasting latent profiles, such as differences in entropy or compressibility. Guided by these insights, we design synthetic probes for uncertainty and symbolic reasoning that align with intrinsic metrics while decoupling from leaderboard bias. We recommend reporting LPP alongside benchmarks to provide a deeper, interpretable understanding of model behavior, enabling more reliable model selection, safety assessment, and evaluation beyond surface-level accuracy.

cs.CL↗

arXiv2026

Not All Is Lost: Repairing Lossy User Preference States of Personalization Encoders

Personalization encoders compress evolving interaction histories into preference states used to rank items or condition text generation. A task head operating only on this state can miss useful evidence that remains in the frozen encoder's cached representations for individual timesteps. We study this recoverability gap and propose REPAIR, which compares cached representations with the current preference state in a compact learned coordinate space. It resolves corrective evidence over extended history, recent interactions, and localized bursts. It then selects which patterns at which timesteps contribute and adds their aggregate correction to the state before the task head. Encoder-host repair reuses representations from the existing forward computation without re-encoding the history. Across MovieLens, PENS, MIND, and Amazon Reviews 2023, training only REPAIR improves MRR and nDCG@10 for all twelve representative recommendation hosts while both encoder and task head remain frozen. Head-only finetuning of the same hosts yields smaller gains. For example, Mamba4Rec on MovieLens gains 3.96 MRR points, compared with 0.19 from head-only finetuning. Rank and temporal diagnostics support a compact, host-dependent corrective structure. In personalized generation, IMPerSumm improves the two reported weighted PerSEval variants, which assess responsiveness to user preference, by up to 25.23%. These results support post-compression state correction and distinguish the availability of preference evidence from its downstream use.

cs.LG↗

arXiv2026

Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization

A user's movie, news, and dialogue histories differ in their native actions and outputs, yet each interaction supplies evidence that can update user memory. We study whether these histories can train one reusable update mechanism. An action-on-item schema pairs a mapped interaction role with a content embedding, allowing shared update parameters to operate on separate user states. We establish invariance to native relabeling, bounded state changes under item-embedding perturbations, and a pooled-training bound under explicit compatibility conditions. The Multi-Timescale State Hypothesis (MTSH) specifies how this evidence enters, persists, and is consumed; PerTIDE implements it with action gating, three state-space traces, fusion, and command-conditioned readout. On PENS, the same history encoder supports both next-news prediction and personalized headline generation. In a controlled PENS-to-MovieLens experiment, a frozen source-trained core exceeds an identically structured random core by 15.23 MRR points after fitting the same target consumer. On MIND, PerTIDE retains a 4.12-point MRR advantage over a same-input three-branch state-space control. Action, readout, and trace interventions identify complementary contributions to these gains. Together, the theory and experiments support learning history updates across compatible sources and reusing them through predictive and generative consumers.

cs.LG↗

arXiv2026

Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models

Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implicitly assuming the teacher to be a reliable oracle. In large language models (LLMs), this assumption often fails: teacher predictions can exhibit high entropy and hallucinations, causing standard KD to degrade well-calibrated student priors. We propose CaRE-KD, a confidence-gated distillation framework that replaces static objectives with uncertainty-adaptive optimization. CaRE-KD has two components: a token-level loss (CaRE-Divergence) that adaptively switches between Forward and Reverse KL divergence based on teacher--student confidence, and a batch-level epistemic rejection mechanism (Revival) that suppresses updates when the teacher is more uncertain than the student. We provide a gradient-level analysis showing how this dual-granularity design induces a conditional calibration mechanism that prior static divergences cannot reproduce. Empirically, across eight teacher--student pairs and eleven benchmarks spanning instruction following, chat alignment, code generation, and mathematical reasoning, CaRE-KD delivers consistent gains over strong baselines (Skewed-KL, $α$--$β$ divergence). Highlights include up to $+3.2$ average ROUGE-L on instruction-following tasks, $+2.1$ pass@1 on MBPP, $+1.7$ accuracy on GSM8k, and $+1.8$ accuracy on CollegeMath over the strongest baseline, with consistent gains in LLM-as-a-judge factuality (up to $+2.5$ per task over Skewed-RKL). Revival further acts as a principled, loss-agnostic plug-in that systematically strengthens existing distillation objectives by filtering epistemically unreliable teacher supervision.

cs.CL↗

arXiv2026

COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages

Machine translation (MT) for Indian languages remains constrained by the limited availability of high-quality, Indic-centric parallel corpora and evaluation benchmarks. Existing multilingual resources are largely constructed from English-pivot content and often fail to capture the linguistic diversity, cultural complexity, and domain-specific characteristics of Indian languages. We present COILD, an Indic-centric parallel corpus comprising over 1.16 million human-translated and human-verified sentence pairs, covering 20 Indian language pairs across the Indo-Aryan, Dravidian, Tibeto-Burman, and Austro-Asiatic language families. The corpus is built entirely from original Indian language sources collected from licensed repositories spanning eight domains with direct real-world applicability. Furthermore, we introduce a domain-centric benchmark comprising 2,000 expert-verified sentences to enable consistent multilingual and cross-lingual evaluation across Indian language pairs. To validate the effectiveness of COILD, we fine-tune two representative multilingual neural machine translation models, IndicTrans2-Distilled and NLLB-200. Experimental results demonstrate consistent improvements across language pairs, domains, automatic evaluation metrics, and human evaluation, highlighting the effectiveness of high-quality Indic-centric supervision. COILD provides a valuable training and evaluation resource for advancing multilingual machine translation and future multilingual language models for Indian languages.

cs.CL↗

arXiv2026

Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models

Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such grounding and primarily reason from available evidence alone, creating a mismatch between expert-led and fully automated claim verification. To mitigate this gap, we posit human-AI collaboration as a more promising path forward, where expert feedback, grounded in real-world knowledge and domain expertise, guides the model's reasoning. However, existing LRMs are hard to calibrate to natural language feedback, particularly in a multi-turn interaction setup. We propose Co-FactChecker, a framework for human-AI collaborative claim verification. We introduce a new interaction paradigm that treats the model's thinking trace as a shared scratchpad. Co-FactChecker translates expert feedback into trace-edits that introduce targeted modifications to the trace, sidestepping the shortcomings of dialogue-based interaction. We provide theoretical results showing that trace-editing offers advantages over multi-turn dialogue, and our automatic evaluations demonstrate that Co-FactChecker outperforms existing autonomous and human-AI collaboration approaches. Human evaluations further show that Co-FactChecker is preferred over multi-turn dialogue, producing higher quality reasoning and verdicts along with relatively easier to interpret and more useful thinking traces.

cs.CL↗

arXiv2026

Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique

As scientific literature grows and papers increasingly under-report limitations, multi-agent LLMs offer a promising approach to systematically uncover these hidden failure modes. Here, we introduce Tree-of-Concerns, a multi-agent framework that deploys specialized skeptic personas, each operating through a category-specific analytical lens, as parallel debate trees to extract unstated limitations from scientific papers. Each persona conducts structured, evidence-grounded argumentation, while a Panel Review mechanism re-evaluates each surviving claim from all five perspectives to correct category drift and severity miscalibration. Through retrieval-free, single-paper experiments on ToC-Bench, our benchmark of 414 research papers with 1,905 unstated limitations, sourced from reviewer-reported weaknesses and follow-up citation critiques, we demonstrate that ToC improves precision by 79% and coverage by 11% relative to the strongest baseline, surfacing specific, evidence-grounded concerns that support reviewers in systematic evaluation.

cs.CL↗

arXiv2026

Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages

As Large Language Models (LLMs) develop stronger multilingual capabilities, their sensitivity to culturally diverse entities becomes increasingly important. Prior work by Naous et al. (2024) has shown that LLMs often favor Western-associated entities in Arabic. Due to the lack of entity-centric multilingual benchmarks, it remains unclear if such biases also manifest in various non-Western languages. In this paper, we introduce Camellia, a benchmark for evaluating entity-centric cultural biases in nine Asian languages, spanning six Asian cultures. Camellia includes 19,530 manually annotated entities associated with the covered Asian or Western cultures, as well as 2,173 masked contexts for these entities derived from social media posts. Using Camellia, we evaluate cultural biases in four recent multilingual LLMs across three tasks: cultural context adaptation, sentiment association, and entity extractive QA. Our analyses show that LLMs struggle with cultural adaptation across these languages, with performance differing across models developed in different regions. We further observe that different LLM families can hold distinct biases, reflected in the ways they link cultures to particular sentiments. Lastly, we find that LLMs can struggle with context understanding in some Asian languages, creating performance gaps between cultures in entity extraction.

cs.CL↗

arXiv2026

MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions

The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains scarce. Here we introduce MAGneT, a novel multi-agent framework for synthetic psychological counseling session generation that decomposes counselor response generation into coordinated sub-tasks handled by specialized LLM agents, each modeling a key psychological technique. Unlike prior single-agent approaches, MAGneT better captures the structure and nuance of real counseling. We further propose a unified evaluation framework that consolidates diverse automatic metrics and expands expert assessment from four to nine counseling aspects, thus addressing inconsistencies in prior evaluation protocols. Empirically, MAGneT substantially outperforms existing methods: experts prefer MAGneT-generated sessions in 77.2% of cases on average across the nine aspects over the strongest baseline, and sessions generated by MAGneT using Llama3-8B-Instruct backbone yield 3.2% higher general counseling skills and 4.3% higher CBT-specific skills on cognitive therapy rating scale (CTRS). An open source Llama3-8B-Instruct model fine-tuned on MAGneT-generated data also outperforms models fine-tuned using baseline synthetic datasets by 6.9% on average on CTRS. We make our code, data and fine-tuned model public.

cs.CL↗

arXiv2026

Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling, but adapting them to this safety-critical domain is hindered by limited real-world data due to privacy constraints. Synthetic datasets provide a promising alternative, but existing approaches often rely on unstructured or semi-structured text inputs and overlook structural dependencies between a client's cognitive, emotional, and behavioral states, leading to psychologically inconsistent and less realistic interactions. We introduce Graph2Counsel, a framework for generating synthetic counseling sessions grounded in Client Psychological Graphs (CPGs) that encode relationships among clients' thoughts, emotions, and behaviors. Graph2Counsel uses a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT and Multi-Agent Feedback. It produces 760 sessions from 76 CPGs across diverse client profiles. In expert evaluation, our dataset outperforms prior datasets on specificity, counselor competence, authenticity, conversational flow, and safety (Krippendorff's $α$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on several metrics on CounselingBench and CounselBench, while matching baselines on others. We further introduce Therapy-Eval, a multi-turn evaluation framework, and demonstrate the effectiveness of our fine-tuned model in realistic therapeutic conversations. We make our code, data and fine-tuned model public.

cs.CL↗

arXiv2026

Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation

Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes stylistic control while treating hate speech as homogeneous, overlooking that distinct forms of abuse require fundamentally different counterspeech strategies. To address this gap, we introduce FIRE (Factuality Informed Multi-Agent Reasoning Framework) that first decomposes hate speech into one of the five distinct categories (misinformation, stereotype, conspiracy, dehumanizing, non-factual), and then maps it to a targeted counterspeech style. To facilitate FIRE, we curate FactualCS, a novel dataset of $4,784$ instances that provides the annotations regarding hate categories, reasoning traces, and evidence mappings, which are critical elements for grounded generation that are missing in prior work. A comprehensive evaluation across $28$ baseline configurations demonstrates that FIRE significantly surpasses existing methods, despite using compact agents ($<$2B). FIRE achieves a $\sim$ $12 \%$ and $\sim$ $11 \%$ improvements in factual and category-specific accuracy respectively, while simultaneously reducing toxicity by $\sim$ $11 \%$ relative to the strongest baselines. Further human evaluation confirms that responses generated by FIRE are significantly preferred over the strongest baselines, underscoring its effectiveness for real-world deployment. These findings show that decomposing the underlying intent of hate speech is essential for generating safe, effective, and contextually precise counterspeech.

cs.CL↗

arXiv2026

HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide

Multimodal Large Language Models (MLLMs) can assign similar confidence to answers that fail for different reasons. We propose HalluPrism, a behavioral diagnostic that re-runs an answer after visual degradation, blank-image replacement, and grounding or relation checks. These targeted probes yield a signature over visual-perturbation sensitivity (V ), image-removal confidence retention (L), and grounding/relation-probe instability (A). Across 58K+ examples from four benchmarks and four MLLMs, image-removal confidence retention is most prevalent, while grounding/relation-probe instability better separates failure families. Only 18 of 48 source-target checks are diagonally aligned, so the coordinates should be interpreted jointly rather than as independent causal sources. With the dataset fixed, the joint signature improves failure-family AUROC from 0.634 to 0.769 on HallusionBench and from 0.707 to 0.817 on VizWiz, with smaller gains on POPE and VSR. In pooled XGBoost analysis, AUROC rises from 0.78 with scalar confidence to 0.95 with (V, L, A) and 0.97 when confidence is added. The same signature does not automatically improve correctness ranking. The three tested direct scalarizations can harm it. These results separate failure diagnosis from abstention scoring: multimodal uncertainty should characterize failure structure before it is used to decide whether to abstain or correct.

cs.LG↗

arXiv2026

Pruning Laws for Large Language Models

Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly growing memory and compute requirements, which makes deployment on resource-limited hardware infeasible. Model pruning, a widely used compression technique, reduces inference costs by removing redundant parameters. However, its impact on downstream performance remains unpredictable and is typically assessed only through costly empirical sweeps. To address this gap, we introduce pruning laws, simple and interpretable scaling relations that connect a pruned LLM's post-pruning performance to its unpruned performance and pruning ratio. Across ten LLMs (1.3B-30B parameters), a 20B mixture-of-experts model, three pruning strategies (unstructured, width, and depth), and eight diverse tasks, we show that pruning laws achieve strong predictive accuracy (average extrapolation error less than 7%), reliably quantify performance degradation, and identify critical pruning thresholds beyond which recovery is infeasible. Moreover, we demonstrate that the functional form transfers across dense and mixture-of-experts architectures, pruning methods, and unseen models in zero-shot and one-shot setups, with task- and method-specific coefficients that vary in interpretable ways. These results provide both researchers and practitioners with a principled framework to select pruning strategies, estimate safe pruning ratios without exhaustive tuning, and deploy LLMs efficiently under real-world compute and latency constraints.

cs.CL↗

arXiv2026

When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models

Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under safety-constrained instruction, models frequently abstain from answering questions that remain correctly answerable under default instruction despite receiving identical image-question inputs. This raises a fundamental question: does safety alignment suppress perceptual grounding itself, or does visual evidence remain internally available while generation is redirected toward abstention? In this work, we investigate the internal decoding dynamics underlying safety-induced abstention in aligned VLMs. Across multiple architectures and multimodal benchmarks, we show that abstained generations remain consistently influenced by visual evidence throughout decoding, indicating that perceptual grounding is largely preserved despite refusal behavior. We further demonstrate that, although the representational organization of refusal differs substantially across architectures, safety-constrained instruction consistently alters late-stage hidden-state dynamics toward refusal-oriented decoding. Finally, through targeted activation-level interventions, we show that suppressing refusal-related representations reliably restores grounded answering behavior across models without retraining or modifying visual inputs. Together, these findings reveal a previously underexplored failure mode in aligned VLMs: safety alignment can override grounded visual expression even when perceptual evidence remains internally preserved.

cs.CV↗

arXiv2026

Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets. We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components to yield conditionally optimal parameter allocations with respect to fixed importance estimates, followed by a fine-grained pruning stage to meet strict budget constraints. We introduce the Compression Ratio Adherence Factor (CRAFT) to quantify budget fidelity, showing that while existing pruners deviate from target compression ratios by up to 33%, SNIPER achieves near-exact adherence with a CRAFT score of 0.98. Evaluations across four diverse architectures over a set of 18 tasks spanning five domains demonstrate SNIPER's consistent improvements in average performance retention and task-level stability over six state-of-the-art pruners. Across all pruning configurations, SNIPER achieves an excellent mean rank of 1.25, indicating its robust cross-architectural generalizability and excellent reliability.

cs.CL↗