paper-with-me

Papers Arithmetic Reasoning

“Arithmetic Reasoning” 태그가 달린 논문 214편 · 필터 해제

Dual-Manifold Geometry Guided Representation Learning: Adaptive Coupling between Kernel and Data Spaces

2026-08-13 · Wencong Zhang, Yue Zhang, Meiyan Huang, Wei Yang 외 arxiv

Deep representation learning has primarily focused on how features evolve across network layers, while largely overlooking the structured geometry embedded in network parameters. We introduce a dual-manifold perspective …

Representation LearningArithmetic ReasoningImage Classification

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

2026-07-29 · Amirmohammad Farzaneh, Osvaldo Simeone arxiv

LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control of physical AI systems. Yet, when deployed at the edge, the…

Multi-hop Question AnsweringArithmetic ReasoningCode Generation

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

2026-07-01 · Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini hf

In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads perform this synthesis matte…

Arithmetic Reasoning

NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries

2026-06-29 · Aydin Javadov, Shyngys Aitkazinov, Tobias Hoesli, Florian von Wangenheim 외 arxiv

A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training primarily amplifying rather than introducing them. However, this evidence…

Arithmetic ReasoningCode GenerationDecision Making

Arithmetic Pedagogy for Language Models

2026-06-03 · Andhika Bernard Lumbantobing, Hokky Situngkir arxiv

We investigate whether methods of human mathematics pedagogy can guide the training of language models toward arithmetic reasoning. Building on the GASING method -- an Indonesian pedagogy that solves basic arithmetic thr…

Reinforcement LearningArithmetic Reasoning

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

2026-06-02 · Malia Barker, Bishal Lakha, Edoardo Serra, Francesco Gullo arxiv

Large language models achieve strong performance on arithmetic reasoning benchmarks, and one common response to arithmetic brittleness is to delegate computation to code. Yet models are still often used in settings where…

Arithmetic Reasoning

Strategic Over-Parameterization for Generalizable Low-Rank Adaptation

2026-05-15 · Jing Gao, Zhong-Yi Lu, Pan Zhang, Ze-Feng Gao arxiv

Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impractical due to its computational and memory demands. Parameter-efficient fine-tuning (PEFT) approaches such as Low-Rank A…

parameter-efficient fine-tuningArithmetic ReasoningCode Generation

Probabilistic Calibration Is a Trainable Capability in Language Models

2026-05-12 · Davide Baldelli, Sruthi Kuriakose, Maryam Hashemzadeh, Amal Zouaq 외 arxiv

Language models are increasingly used in settings where outputs must satisfy user-specified randomness constraints, yet their generation probabilities are often poorly calibrated to those targets. We study whether this c…

Arithmetic Reasoning

Knowledge Graphs, the Missing Link in Agentic AI-based Formal Verification

2026-05-07 · Vaisakh Naduvodi Viswambharan, Keerthan Kopparam Radhakrishna, Deepak Narayan Gadde, Aman Kumar arxiv

Recent advances in Large Language Models (LLMs) have enabled workflows that generate SystemVerilog Assertions (SVAs) from natural-language specifications, with the potential to accelerate Formal Verification (FV). Howeve…

Arithmetic ReasoningKnowledge Graphs

What Do Claim Verification Datasets Actually Test? A Reasoning Trace Analysis

2026-04-02 · Delip Rao, Chris Callison-Burch arxiv

Despite rapid progress in claim verification, we lack a systematic understanding of what reasoning these benchmarks actually exercise. We generate structured reasoning traces for 24K claim-verification examples across 9 …

Arithmetic Reasoning

Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

2026-03-24 · Aditya Kakade, Vivek Srivastava, Shirish Karande arxiv

Gödel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, Gödel agent for compact models that performs policy repair…

Arithmetic Reasoning

Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation

2026-03-20 · Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee arxiv

We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited to correct model behavior at inference time withou…

Mathematical ReasoningArithmetic Reasoning

ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

2026-03-17 · Tik Yu Yim, Wenting Tan, Sum Yee Chan, Tak-Wah Lam 외 arxiv

Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show th…

Arithmetic ReasoningDomain Adaptation

Large Language Models for Math Education in Low-Resource Languages: A Study in Sinhala and Tamil

2026-02-16 · Sukumar Kishanthan, Kumar Thushalika, Buddhi Jayasekara, Asela Hevapathige arxiv

Large language models (LLMs) have achieved strong results in mathematical reasoning, and are increasingly deployed as tutoring and learning support tools in educational settings. However, their reliability for students w…

Mathematical ReasoningArithmetic Reasoning

$\mathcal{X}$-KD: General Experiential Knowledge Distillation for Large Language Models

2026-02-13 · Yuang Cai, Yuyu Yuan arxiv

Knowledge Distillation (KD) for Large Language Models (LLMs) has become increasingly important as models grow in size and complexity. While existing distillation approaches focus on imitating teacher behavior, they often…

Knowledge DistillationReinforcement LearningArithmetic ReasoningMachine Translation

Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective

2026-01-30 · Shaorong Zhang, Longxuan Yu, Rob Brekelmans, Luhan Tang 외 arxiv

Masked Diffusion Models (MDMs) significantly accelerate inference by trading off sequential determinism. However, the theoretical mechanisms governing generation order and the risks inherent in parallelization remain und…

Arithmetic Reasoning

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

2026-01-09 · Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu 외 arxiv

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these …

Open-Domain Question AnsweringArithmetic ReasoningMachine Translation

The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs

2026-01-04 · Zibo Zhao, Yuanting Zha, Haipeng Zhang, Xingcheng Xu arxiv

Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how a unified optimization objective gives r…

Arithmetic Reasoning

Reliability Under Randomness: An Empirical Analysis of Sparse and Dense Language Models Across Decoding Temperatures

2026-01-02 · Kabir Grover arxiv

The increasing prevalence of sparse Mixture-of-Experts (MoE) architectures in large language models raises important questions regarding their reliability under stochastic decoding. While conditional computation enables …

Computational EfficiencyArithmetic Reasoning

LLMBoost: Make Large Language Models Stronger with Boosting

2025-12-26 · Zehao Chen, Tianxiang Ai, Yifei Li, Gongxun Li 외 arxiv

Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich int…

Arithmetic ReasoningEnsemble Learning
1–20 / 214 다음 →