arXiv subjects

Neeraj Varshney

Publications and source records attributed to Neeraj Varshney.

At least 19 recordsLinked to original sources

arXiv2026

ISAC in 3GPP: Evolution Toward 6G

Integrated sensing and communication (ISAC) is emerging as an important direction in the Third Generation Partnership Project (3GPP) evolution toward 6G because it allows cellular networks to provide environmental awareness in addition to connectivity. This paper surveys the current 3GPP trajectory from Release~19 feasibility studies to Release~20 radio, protocol, and architecture studies, while distinguishing established requirements, ongoing study assumptions, and possible forward directions. The survey covers service requirements, sensing topologies, channel model evolution beyond 3GPP Technical Report (TR)~38.901, Radio Access Network Working Group~1 (RAN1) physical layer design, Radio Access Network Working Groups~2 and~3 (RAN2 and RAN3) system implications, and the role of sensing-assisted communication. It also synthesizes the main unresolved issues in waveform and reference signal design, multi-node coordination, sensing data reporting, service exposure, privacy, and implementation constraints. By connecting service-level motivations to physical layer, protocol, and architecture implications, the paper provides a standards-centric reading of how 3GPP may evolve toward practical 6G ISAC support.

cs.NI↗

arXiv2026

Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning

The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most languages, are quite limited. Translation offers an alternative: converting an input into the model's dominant language unlocks its full capabilities at once. But translating every input is wasteful for languages the model already handles, while leaving the choice to the model fails too, as LLMs are overconfident and skip the tool even when they cannot understand the input. Prior work resolves this with language-specific rules, heuristics, or external routers, each requiring manual engineering. We instead learn a single policy that decides when to translate from reward alone, developing language- and domain-adaptive introspection that invokes translation only when it cannot solve a task natively. Using data from our answer-preserving translation pipeline, we continue RL on the post-trained Qwen3-4B across 22 languages in 3 resource tiers (High, Low, XLow) and 5 domains, and introduce confidence-gated GSPO for cost-sensitive tool use. The gated policy lifts reward over the untrained baseline by +4.6 on High, +23.5 on Low, and +17.5 on XLow, and extends zero-shot to 9 held-out languages. Against an unconstrained policy that almost always translates (the reward upper bound), it preserves full reward at 66% of the cost, outperforming other cost penalties by up to +24.3 on the low-resource tiers while matching the free policy's reward on high-resource tiers at a fraction of the tool use. On 2 synthetic languages with zero prior exposure it correctly learns to always translate, improving +18.7 over the overconfident baseline.

cs.CL↗

arXiv2026

Unlocking Latent Value: Taxonomy-Guided Recovery of High-Performing Data from Low-Tier Web Corpora

Dominant web data curation pipelines for pretraining collapse document quality into a single composite score, systematically missing high-value content along dimensions the scorer underweights. We present a taxonomy-driven framework that recovers this value by filtering along semantically meaningful dimensions that composite scores fail to capture. First, building on the ESSENTIAL-WEB taxonomy, we introduce two novel dimensions: timeliness and cultural specificity, both of which show low pairwise NMI with existing ones. We annotate 14M documents using Qwen2.5 32B and distill into a lightweight 0.5B model. To enable rapid corpus-wide annotation, we additionally train a 73M multi-task MLP on E5 embeddings, achieving 50x inference throughput. Second, to navigate the combinatorial explosion of filter configurations, we introduce a compute-efficient two-pass framework: Pass 1 identifies the strongest dimension signals at small scale; Pass 2 constructs and evaluates conjunctive and disjunctive compound filters from the top performers - identifying high-performing configurations at a fraction of full scaling-law cost. Applying the selected filters to deprioritized web data, taxonomy-filtered subsets outperform their unfiltered baselines and even surpass the highest-quality tier. On mid-tier data, our best filter improves over its unfiltered baseline by 12.1% on reasoning, 9.5% on coding, and 2.0% on knowledge benchmarks, exceeding unfiltered top-tier data by 6.7% on reasoning and 13.7% on coding. Furthermore, filtered data from two tiers below the typical production threshold improves by 22.3% on reasoning and 19.5% on coding over its unfiltered baseline, surpassing top-tier data on coding benchmarks. These results establish that vast latent value remains locked in deprioritized web data, and that multi-dimensional taxonomy filtering is a principled, compute-efficient key to unlocking it.

cs.CL↗

arXiv2026

Multi-TRP Assisted UAV Detection in 3GPP 5G-Advanced ISAC Network

ISAC is currently being standardized within the 3GPP New Radio (NR) to enable cellular infrastructure to perform sensing using existing communication waveforms. While standardization is progressing, practical deployment may be limited by scenario-dependent observability constraints. For example, in UMa-AV scenarios, sensing with a single TRP can be affected by restricted angular coverage, partial blockage, and limited field of view, which may degrade detection reliability in three-dimensional UAV environments. For this reason, multi-TRP solutions have been suggested to improve spatial diversity and sensing robustness. In this paper, we present a system-level investigation of multi-TRP assisted monostatic sensing for UAV detection under standardized 3GPP UMa-AV channel assumptions and Release 19 evaluation parameters. We propose a spatial diversity fusion framework and evaluate the achievable performance of a 3GPP network by combining the measurements obtained independently at different TRP. Extensive evaluations demonstrate that multi-TRP assistance improves target observability, reduces spurious detections, and tightens localization error distributions at the cost of additional sensing overhead due to the need for multiple TRPs to periodically allocate radio resources for sensing measurements. In the evaluated scenario, results show that a voting threshold of two assisting TRPs achieves an optimal trade-off between miss detection probability and false alarm suppression, meeting 3GPP performance objectives. Furthermore, we quantify the sensing overhead and show that proper system design, tuned to the application requirements, can substantially reduce its impact: for example, extending the sensing refresh interval beyond the 128 ms coherent processing interval to 1 s reduces the effective overhead from 29 % to approximately 3.7 %, enabling more scalable network deployment.

cs.IT↗

arXiv2026

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts

Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws show that under fixed active computation, model quality scales predictably with total parameters, and MoEs realize this by increasing expert count. However, training large MoEs is expensive, as memory requirements and inter-device communication both scale with total parameter count. We propose expert upcycling, a method for progressively expanding MoE capacity by increasing the number of experts during continued pre-training (CPT). Given a trained E-expert model, the upcycling operator constructs an mE-expert model through expert duplication and router extension while holding top-K routing fixed, preserving per-token inference cost. Duplication provides a warm initialization: the expanded model inherits the source checkpoint's learned representations, starting from a substantially lower loss than random initialization. Subsequent CPT then breaks the symmetry among duplicated experts to drive specialization. We formalize the upcycling operator and develop a theoretical framework decomposing the quality gap into a capacity term and an initialization term. We further introduce utility-based expert selection, which uses gradient-based importance scores to guide non-uniform duplication, more than tripling gap closure when CPT is limited. In our 7B-13B total parameter experiments, the upcycled model matches the fixed-size baseline on validation loss while saving 32% of GPU hours. Comprehensive ablations across model scales, activation ratios, MoE architectures, and training budgets yield a practical recipe for deploying expert upcycling, establishing it as a principled, compute-efficient alternative to training large MoE models from scratch.

cs.LG↗

arXiv2026

Evaluation of gNB Monostatic Sensing for UAV Use Case

3GPP Release 19 has initiated the standardization of integrated sensing and communications (ISAC), including a channel model for monostatic sensing, evaluation scenarios, and performance assessment methodologies. These common assumptions provide an important basis for ISAC evaluation, but reproducible end-to-end studies still require a transparent sensing implementation. This paper evaluates 5G New Radio (NR) base station (gNB)-based monostatic sensing for the Unmanned Aerial Vehicle (UAV) use case using a 5G NR downlink Cyclic Prefix-Orthogonal Frequency Division Multiplexing (CP-OFDM) waveform and positioning reference signals (PRS), following 3GPP Urban Macro-Aerial Vehicle (UMa-AV) scenario assumptions. We present an end-to-end processing chain for multi-target detection and 3D localization, achieving more than 70% detection probability with less than 5% false alarm rate, in the considered scenario. For correctly detected targets, localization errors are on the order of a few meters, with a 90th-percentile error of 4m and 6m in the vertical and horizontal directions, respectively. To support reproducible baseline studies and further research, we release the simulator 5GNRad, which reproduces our evaluation

eess.SP↗

arXiv2026

Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs

Code-mixing and code-switching (CSW) remain challenging phenomena for large language models (LLMs). Despite recent advances in multilingual modeling, LLMs often struggle in mixed-language settings, exhibiting systematic degradation in grammaticality, factuality, and safety behavior. This work provides a comprehensive overview of CSW research in modern large language model settings. We introduce a unifying taxonomy that organizes prior work along dimensions of data, modeling, and evaluation, and we distill these findings into a practical playbook of actionable recommendations for building, adapting, and evaluating CSW-capable LLMs. We review modeling approaches ranging from CSW-tailored pre-training and task-specific post-training to prompting strategies and in-context learning. We analyze current evaluation practices, highlighting sources of instability and limited reproducibility, and we catalog existing benchmarks while critically examining their linguistic coverage and English-centric biases. Finally, we discuss emerging safety concerns, including use of code-mixing as a mechanism for bypassing model safeguards, and identify open research challenges.

cs.CL↗

arXiv2025

Toward Honest Language Models for Deductive Reasoning

Deductive reasoning is the process of deriving conclusions strictly from the given premises, without relying on external knowledge. We define honesty in this setting as a model's ability to respond only when the conclusion is logically entailed by the premises, and to abstain otherwise. However, current language models often fail to reason honestly, producing unwarranted answers when the input is insufficient. To study this challenge, we formulate honest deductive reasoning as multi-step tasks where models must either derive the correct conclusion or abstain. We curate two datasets from graph structures, one for linear algebra and one for logical inference, and introduce unanswerable cases by randomly perturbing an edge in half of the instances. We find that prompting and existing training methods, including GRPO with or without supervised fine-tuning initialization, struggle on these tasks. In particular, GRPO optimize only for final task outcomes, leaving models vulnerable to collapse when negative rewards dominate early training. To address this, we propose ACNCHOR, a reinforcement learning method that injects ground truth trajectories into rollouts, preventing early training collapse. Our results demonstrate that this method stabilizes learning and significantly improves the overall reasoning performance, underscoring the importance of training dynamics for enabling honest deductive reasoning in language models.

cs.CL↗

arXiv2025

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness

As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison of "thinking" and "non-thinking" LLMs in the LLM-as-a-judge paradigm using open-source Qwen 3 models of relatively small sizes (0.6B, 1.7B, and 4B parameters). We evaluate both accuracy and computational efficiency (FLOPs) on RewardBench tasks, and further examine augmentation strategies for non-thinking models, including in-context learning, rubric-guided judging, reference-based evaluation, and n-best aggregation. Our results show that despite these enhancements, non-thinking models generally fall short of their thinking counterparts. Our results show that thinking models achieve approximately 10% points higher accuracy with little overhead (under 2x), in contrast to augmentation strategies like few-shot learning, which deliver modest gains at a higher cost (>8x). Bias and robustness analyses further demonstrate that thinking models maintain significantly greater consistency under a variety of bias conditions such as positional, bandwagon, identity, diversity, and random biases (6% higher on average). We further extend our experiments to the multilingual setting and our results confirm that explicit reasoning extends its benefits beyond English. Overall, our work results in several important findings that provide systematic evidence that explicit reasoning offers clear advantages in the LLM-as-a-judge paradigm not only in accuracy and efficiency but also in robustness.

cs.AI↗

arXiv2025

Deep Learning-based Human Gesture Channel Modeling for Integrated Sensing and Communication Scenarios

With the development of Integrated Sensing and Communication (ISAC) for Sixth-Generation (6G) wireless systems, contactless human recognition has emerged as one of the key application scenarios. Since human gesture motion induces subtle and random variations in wireless multipath propagation, how to accurately model human gesture channels has become a crucial issue for the design and validation of ISAC systems. To this end, this paper proposes a deep learning-based human gesture channel modeling framework for ISAC scenarios, in which the human body is decomposed into multiple body parts, and the mapping between human gestures and their corresponding multipath characteristics is learned from real-world measurements. Specifically, a Poisson neural network is employed to predict the number of Multi-Path Components (MPCs) for each human body part, while Conditional Variational Auto-Encoders (C-VAEs) are reused to generate the scattering points, which are further used to reconstruct continuous channel impulse responses and micro-Doppler signatures. Simulation results demonstrate that the proposed method achieves high accuracy and generalization across different gestures and subjects, providing an interpretable approach for data augmentation and the evaluation of gesture-based ISAC systems.

eess.SP↗

arXiv2024

Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models

As Large Language Models (LLMs) continue to exhibit remarkable performance in natural language understanding tasks, there is a crucial need to measure their ability for human-like multi-step logical reasoning. Existing logical reasoning evaluation benchmarks often focus primarily on simplistic single-step or multi-step reasoning with a limited set of inference rules. Furthermore, the lack of datasets for evaluating non-monotonic reasoning represents a crucial gap since it aligns more closely with human-like reasoning. To address these limitations, we propose Multi-LogiEval, a comprehensive evaluation dataset encompassing multi-step logical reasoning with various inference rules and depths. Multi-LogiEval covers three logic types--propositional, first-order, and non-monotonic--consisting of more than 30 inference rules and more than 60 of their combinations with various depths. Leveraging this dataset, we conduct evaluations on a range of LLMs including GPT-4, ChatGPT, Gemini-Pro, Yi, Orca, and Mistral, employing a zero-shot chain-of-thought. Experimental results show that there is a significant drop in the performance of LLMs as the reasoning steps/depth increases (average accuracy of ~68% at depth-1 to ~43% at depth-5). We further conduct a thorough investigation of reasoning chains generated by LLMs which reveals several important findings. We believe that Multi-LogiEval facilitates future research for evaluating and enhancing the logical reasoning ability of LLMs. Data is available at https://github.com/Mihir3009/Multi-LogiEval.

cs.CL↗

arXiv2024

Efficient Transmission Scheme for LEO Satellite-Based NB-IoT: A Data-Driven Perspective

This study analyses the medium access control (MAC) layer aspects of a low-Earth-orbit (LEO) satellite-based Internet of Things (IoT) network. A transmission scheme based on change detection is proposed to accommodate more users within the network and improve energy efficiency. Machine learning (ML) algorithms are also proposed to reduce the payload size by leveraging the correlation among the sensed parameters. Real-world data from an IoT testbed deployed for a smart city application is utilised to analyse the performance regarding collision probability, effective data received and average battery lifetime. The findings reveal that the traffic pattern, post-implementation of the proposed scheme, differs from the commonly assumed Poisson traffic, thus proving the effectiveness of having IoT data from actual deployment. It is demonstrated that the transmission scheme facilitates accommodating more devices while targeting a specific collision probability. Considering the link budget for a direct access NB-IoT scenario, more data is effectively offloaded to the server within the limited visibility of LEO satellites. The average battery lifetimes are also demonstrated to increase by many folds by using the proposed access schemes and ML algorithms.

eess.SP↗

arXiv2024

Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, they have been shown to suffer from a critical limitation pertinent to 'hallucination' in their output. Recent research has focused on investigating and addressing this problem for a variety of tasks such as biography generation, question answering, abstractive summarization, and dialogue generation. However, the crucial aspect pertaining to 'negation' has remained considerably underexplored. Negation is important because it adds depth and nuance to the understanding of language and is also crucial for logical reasoning and inference. In this work, we address the above limitation and particularly focus on studying the impact of negation in LLM hallucinations. Specifically, we study four tasks with negation: 'false premise completion', 'constrained fact generation', 'multiple choice question answering', and 'fact generation'. We show that open-source state-of-the-art LLMs such as LLaMA-2-chat, Vicuna, and Orca-2 hallucinate considerably on all these tasks involving negation which underlines a critical shortcoming of these models. Addressing this problem, we further study numerous strategies to mitigate these hallucinations and demonstrate their impact.

cs.CL↗

arXiv2024

Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies

This study explores the sycophantic tendencies of Large Language Models (LLMs), where these models tend to provide answers that match what users want to hear, even if they are not entirely correct. The motivation behind this exploration stems from the common behavior observed in individuals searching the internet for facts with partial or misleading knowledge. Similar to using web search engines, users may recall fragments of misleading keywords and submit them to an LLM, hoping for a comprehensive response. Our empirical analysis of several LLMs shows the potential danger of these models amplifying misinformation when presented with misleading keywords. Additionally, we thoroughly assess four existing hallucination mitigation strategies to reduce LLMs sycophantic behavior. Our experiments demonstrate the effectiveness of these strategies for generating factually correct statements. Furthermore, our analyses delve into knowledge-probing experiments on factual keywords and different categories of sycophancy mitigation.

cs.CL↗

arXiv2024

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models

Recently developed large language models (LLMs) have been shown to perform remarkably well on a wide range of language understanding tasks. But, can they really "reason" over the natural language? This question has been receiving significant research attention and many reasoning skills such as commonsense, numerical, and qualitative have been studied. However, the crucial skill pertaining to 'logical reasoning' has remained underexplored. Existing work investigating this reasoning ability of LLMs has focused only on a couple of inference rules (such as modus ponens and modus tollens) of propositional and first-order logic. Addressing the above limitation, we comprehensively evaluate the logical reasoning ability of LLMs on 25 different reasoning patterns spanning over propositional, first-order, and non-monotonic logics. To enable systematic evaluation, we introduce LogicBench, a natural language question-answering dataset focusing on the use of a single inference rule. We conduct detailed analysis with a range of LLMs such as GPT-4, ChatGPT, Gemini, Llama-2, and Mistral using chain-of-thought prompting. Experimental results show that existing LLMs do not fare well on LogicBench; especially, they struggle with instances involving complex reasoning and negations. Furthermore, they sometimes overlook contextual information necessary for reasoning to arrive at the correct conclusion. We believe that our work and findings facilitate future research for evaluating and enhancing the logical reasoning ability of LLMs. Data and code are available at https://github.com/Mihir3009/LogicBench.

cs.CL↗

arXiv2023

The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness

As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark: a collection of diverse safe and unsafe prompts with carefully designed evaluation methods that facilitate systematic evaluation, comparison, and analysis over 'safety' and 'over-defensiveness.' With SODE, we study a variety of LLM defense strategies over multiple state-of-the-art LLMs, which reveals several interesting and important findings, such as (a) the widely popular 'self-checking' techniques indeed improve the safety against unsafe inputs, but this comes at the cost of extreme over-defensiveness on the safe inputs, (b) providing a safety instruction along with in-context exemplars (of both safe and unsafe inputs) consistently improves safety and also mitigates undue over-defensiveness of the models, (c) providing contextual knowledge easily breaks the safety guardrails and makes the models more vulnerable to generating unsafe responses. Overall, our work reveals numerous such critical findings that we believe will pave the way and facilitate further research in improving the safety of LLMs.

cs.CL↗

arXiv2023

Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we propose to instruction tune LLMs with additional explicit losses from the intermediate layers (LITE) and show that it enables these layers to acquire 'good' generation ability without affecting the generation ability of the final layer. We perform 'dynamic confidence-based early exiting' at token level from the intermediate layers which improves the efficiency of text generation without compromising the quality of the generation. We conduct comprehensive experiments by instruction tuning LLaMA-2 models on the Alpaca dataset and holistically evaluate on four different human-instruction test sets. We show that dynamic early exiting achieves consistent and considerable inference computation cost improvements (37.86% for 7B and 46.35% for 13B model) while maintaining the generation quality of the responses. We further conduct a thorough analysis of the results over several important aspects, such as comparing the semantic similarity of the outputs and dissecting the efficiency improvements by comparing the number of tokens generated in the output. In summary, our work contributes to improving the efficiency of LLM inference while maintaining the generation quality, a crucial step en route to enabling their widespread adoption.

cs.CL↗

arXiv2023

Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models

Logical reasoning is fundamental for humans yet presents a substantial challenge in the domain of Artificial Intelligence. Initially, researchers used Knowledge Representation and Reasoning (KR) systems that did not scale and required non-trivial manual effort. Recently, the emergence of large language models (LLMs) has demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems. Consequently, there's a growing interest in using LLMs for logical reasoning via natural language. This work strives to understand the proficiency of LLMs in logical reasoning by offering a brief review of the latest progress in this area; with a focus on the logical reasoning datasets, tasks, and the methods adopted to utilize LLMs for reasoning. To offer a thorough analysis, we have compiled a benchmark titled LogiGLUE. This includes 24 varied datasets encompassing deductive, abductive, and inductive reasoning. Utilizing LogiGLUE as a foundation, we have trained an instruction fine-tuned language model, resulting in LogiT5. We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model across the different logical reasoning categories. We also assess various LLMs using LogiGLUE, and the findings indicate that LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning. We aim to shed light on the capabilities and potential pathways for enhancing logical reasoning proficiency in LLMs, paving the way for more advanced and nuanced developments in this critical field.

cs.CL↗