Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
Fine-tuning on generalized tasks such as instruction following, code generation, and mathematics has been shown to enhance language models' performance on a range of tasks. Nevertheless, explanations of how such fine-tuning influences the internal computations in these models remain elusive. We study how fine-tuning affects the internal mechanisms implemented in language models. As a case study, we explore the property of entity tracking, a crucial facet of language comprehension, where models fine-tuned on mathematics have substantial performance gains. We identify the mechanism that enables entity tracking and show that (i) in both the original model and its fine-tuned versions primarily the same circuit implements entity tracking. In fact, the entity tracking circuit of the original model on the fine-tuned versions performs better than the full original model. (ii) The circuits of all the models implement roughly the same functionality: Entity tracking is performed by tracking the position of the correct entity in both the original model and its fine-tuned versions. (iii) Performance boost in the fine-tuned models is primarily attributed to its improved ability to handle the augmented positional information. To uncover these findings, we employ: Patch Patching, DCM, which automatically detects model components responsible for specific semantics, and CMAP, a new approach for patching activations across models to reveal improved mechanisms. Our findings suggest that fine-tuning enhances, rather than fundamentally alters, the mechanistic operation of the model.
Code (0)
등록된 구현이 없습니다.
Tasks
Code GenerationInstruction FollowingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process…
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and de…
Spatial ReasoningDetecting and Pruning Prominent but Detrimental Neurons in Large Language Models
Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. W…
INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation
Autonomous driving systems face significant challenges in handling unpredictable edge-case scenarios, such as adversarial pedestrian movements, dangerous vehicle maneuvers, and sudden environmental changes. Current end-t…
Autonomous DrivingDecision MakingLanguage ModelingLanguage ModellingReasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their final answers often contradict their own re…
Reinforcement Learning