REVIEW 7 cited by
Forgetting Transformer: Softmax Attention with a Forget Gate
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
Signed reviews
read the original abstract
An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the unnormalized attention scores in a data-dependent way. We name this attention mechanism Forgetting Attention and the resulting model the Forgetting Transformer (FoX). We show that FoX outperforms the Transformer on long-context language modeling, length extrapolation, and short-context downstream tasks, while performing on par with the Transformer on long-context downstream tasks. Moreover, it is compatible with the FlashAttention algorithm and does not require any positional embeddings. Several analyses, including the needle-in-the-haystack test, show that FoX also retains the Transformer's superior long-context capabilities over recurrent sequence models such as Mamba-2, HGRN2, and DeltaNet. We also introduce a "Pro" block design that incorporates some common architectural components in recurrent sequence models and find it significantly improves the performance of both FoX and the Transformer. Our code is available at https://github.com/zhixuan-lin/forgetting-transformer.
Forward citations
Cited by 7 Pith papers
-
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
MesaNet uses conjugate-gradient-optimal test-time regression in a chunkwise-parallelizable recurrent layer, achieving strong language modeling and benchmark performance at up to 1B scale.
-
Raven: High-Recall Sequence Modeling with Sparse Memory Routing
Raven is a linear-time sequence model whose sparse, input-dependent routing writes tokens into dedicated memory slots, preserving long-context recall and extrapolating 16x beyond training length.
-
Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
A gated Shift-FFN adapter that adds the previous token's representation to the current token's before the feedforward layer reduces repetitive looping and improves math accuracy in LoRA fine-tuned models trained on lo...
-
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
Self-correction blind spots in residual-stream autoregressive models arise iff the product of attention Jacobians has spectral radius ≥1, with a sharp marker threshold and RL coupling condition derived from that radius.
-
Distributed Dynamic Associative Memory via Online Convex Optimization
Tree-based distributed online gradient descent gives sublinear static regret and path-length-dependent dynamic regret for heterogeneous multi-agent associative memory with communication delays.
-
Scaling Context Requires Rethinking Attention
On 64k-token natural language training, power attention with degree 2 achieves lower loss per FLOP than both softmax attention and existing linear attention, and its GPU kernels run faster than Flash Attention at long...
-
Understanding Transformer from the Perspective of Associative Memory
Frames the Transformer as associative memory, derives retrieval SNR for linear, softmax, ReLU, and SoLU kernels, and proposes DeltaFormer, a softmax-plus-delta-rule variant claimed to exceed TC0 expressivity.
Discussion (0). Continue with ORCID to comment.