REVIEW 7 cited by
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmetic reasoning as a representative task. Using causal analysis, we identify a subset of the model (a circuit) that explains most of the model's behavior for basic arithmetic logic and examine its functionality. By zooming in on the level of individual circuit neurons, we discover a sparse set of important neurons that implement simple heuristics. Each heuristic identifies a numerical input pattern and outputs corresponding answers. We hypothesize that the combination of these heuristic neurons is the mechanism used to produce correct arithmetic answers. To test this, we categorize each neuron into several heuristic types-such as neurons that activate when an operand falls within a certain range-and find that the unordered combination of these heuristic types is the mechanism that explains most of the model's accuracy on arithmetic prompts. Finally, we demonstrate that this mechanism appears as the main source of arithmetic accuracy early in training. Overall, our experimental results across several LLMs show that LLMs perform arithmetic using neither robust algorithms nor memorization; rather, they rely on a "bag of heuristics".
Forward citations
Cited by 7 Pith papers
-
Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks
Learned replacement non-linearities show transformers are rarely optimal for algorithmic tasks, with benefits that are task-specific, while language/code gains are smaller and more transferable.
-
Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs
Llama-3 arithmetic is computed by a shared neuron set across symbolic, text, and code formats, and cross-format failures are activation-state differences, not distinct circuits.
-
All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens
LLMs solve arithmetic in-context via an All-for-One pattern, with all input-specific computation occurring at the last token after a two-layer information transfer window.
-
Modular Arithmetic: Language Models Solve Math Digit by Digit
LLMs perform 3-digit addition and subtraction via digit-position-specific MLP circuits that can be intervened upon to change individual output digits.
-
Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs
In LLaMA-3-8B-Instruct, addition information becomes linearly decodable in a fixed layer-wise order: formula structure, carries and sums, result digits, then output generation.
-
Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
Neuron-Fusion selectively restores large-change neurons from a fine-tuned multimodal model and suppresses small changes, improving language retention with modest visual trade-offs.
-
Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation
A taxonomy-driven survey arguing that reward design is the central mechanism shaping reliable LLM reasoning, with maps of reward paradigms, reward-hacking failure modes, and benchmark pitfalls.
Discussion (0). Continue with ORCID to comment.