惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园_首页
Vercel News
Vercel News
月光博客
月光博客
S
SegmentFault 最新的问题
A
About on SuperTechFans
Microsoft Security Blog
Microsoft Security Blog
U
Unit 42
Google DeepMind News
Google DeepMind News
Engineering at Meta
Engineering at Meta
B
Blog RSS Feed
Y
Y Combinator Blog
云风的 BLOG
云风的 BLOG
N
Netflix TechBlog - Medium
小众软件
小众软件
WordPress大学
WordPress大学
G
Google Developers Blog
Recent Announcements
Recent Announcements
H
Hackread – Cybersecurity News, Data Breaches, AI and More
P
Proofpoint News Feed
Blog — PlanetScale
Blog — PlanetScale
MongoDB | Blog
MongoDB | Blog
F
Fortinet All Blogs
博客园 - 【当耐特】
I
InfoQ

cs.CL updates on arXiv.org

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents A Triadic Suffix Tokenization Scheme for Numerical Reasoning Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method CocoaBench: Evaluating Unified Digital Agents in the Wild MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis Evaluating Memory Capability in Continuous Lifelog Scenario How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical Contexts Efficient Training for Cross-lingual Speech Language Models Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities Uncertainty-Aware Web-Conditioned Scientific Fact-Checking When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies When Verification Fails: How Compositionally Infeasible Claims Escape Rejection Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series
From Indirect Object Identification to Syllogisms: Explor...
Karim Saraipour, Shichang Zhang · 2025-08-22 · via cs.CL updates on arXiv.org

Transformer-based language models (LMs) can perform a wide range of tasks, and mechanistic interpretability (MI) aims to reverse engineer the components responsible for task completion to understand their behavior. Previous MI research has focused on linguistic tasks such as Indirect Object Identification (IOI). In this paper, we investigate the ability of GPT-2 small to handle binary truth values by analyzing its behavior with syllogistic prompts, e.g., "Statement A is true. Statement B matches statement A. Statement B is", which requires more complex logical reasoning compared to IOI. Through our analysis of several syllogism tasks of varying difficulty, we identify multiple circuits that mechanistically explain GPT-2's logical-reasoning capabilities and uncover binary mechanisms that facilitate task completion, including the ability to produce a negated token not present in the input prompt through negative heads. Our evaluation using a faithfulness metric shows that a circuit comprising five attention heads achieves over 90% of the original model's performance. By relating our findings to IOI analysis, we provide new insights into the roles of specific attention heads and MLPs in LMs. These insights contribute to a broader understanding of model reasoning and support future research in mechanistic interpretability.