paper-with-me

Papers

Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models

2025-04-14 · Thilo Hagendorff, Sarah Fabi

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities has been made by scaling test-time compute. However, understanding and quantifying model-internal reasoning abilities - the inferential "leaps" models make between individual token predictions - remains crucial. This study introduces a benchmark (n = 4,000 items) designed to quantify model-internal reasoning in different domains. We achieve this by having LLMs indicate the correct solution to reasoning problems not through descriptive text, but by selecting a specific language of their initial response token that is different from English, the benchmark language. This not only requires models to reason beyond their context window, but also to overrise their default tendency to respond in the same language as the prompt, thereby posing an additional cognitive strain. We evaluate a set of 18 LLMs, showing significant performance variations, with GPT-4.5 achieving the highest accuracy (74.7%), outperforming models like Grok-2 (67.2%), and Llama 3.1 405B (65.6%). Control experiments and difficulty scaling analyses suggest that while LLMs engage in internal reasoning, we cannot rule out heuristic exploitations under certain conditions, marking an area for future investigation. Our experiments demonstrate that LLMs can "think" via latent-space computations, revealing model-internal inference strategies that need further understanding, especially regarding safety-related concerns such as covert planning, goal-seeking, or deception emerging without explicit token traces.

📄 PDF Abstract BibTeX arXiv:2504.10615

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingDescriptive

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Monet: Reasoning in Latent Visual Space Beyond Images and Language

2025-11-26 · Qixun Wang, Yang Shi, Yifei Wang, Yuanxing Zhang 외 arxiv

"Thinking with images" has emerged as an effective paradigm for advancing visual reasoning, extending beyond text-only chains of thought by injecting visual evidence into intermediate reasoning steps. However, existing m…

Reinforcement LearningVisual Reasoning

Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings

2026-01-31 · Yifei Shao, Kun Zhou, Ziming Xu, Mohammad Atif Quamar 외 arxiv

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problem…

Reinforcement LearningMultimodal Reasoning

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

2026-01-30 · Fanmeng Wang, Haotian Liu, Guojiang Zhao, Hongteng Xu 외 arxiv

While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recent latent reasoning methods attempt to mi…

Computational Efficiency

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains

2025-05-22 · Wenhui Tan, Jiaze Li, Jianzhong Ju, Zhenbo Luo 외

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compre…

Mathematical ReasoningReinforcement Learning (RL)

Parallel Test-Time Scaling for Latent Reasoning Models

2025-10-09 · Runyang You, Yongqi Li, Meng Liu, Wenjie Wang 외 arxiv

Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or searc…