REVIEW 8 cited by
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
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
The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We present Iterative Null-space Projection (INLP), a novel method for removing information from neural representations. Our method is based on repeated training of linear classifiers that predict a certain property we aim to remove, followed by projection of the representations on their null-space. By doing so, the classifiers become oblivious to that target property, making it hard to linearly separate the data according to it. While applicable for multiple uses, we evaluate our method on bias and fairness use-cases, and show that our method is able to mitigate bias in word embeddings, as well as to increase fairness in a setting of multi-class classification.
Forward citations
Cited by 8 Pith papers
-
Emergent Misalignment Recruits a Pre-existing Persona Subspace
Fine-tuning on narrow bad data recruits a low-rank persona subspace already present in a frozen instruction-tuned model; holding that subspace out of activations prevents broad misalignment, and injecting it into the ...
-
Convergent Linear Representations of Emergent Misalignment
A single activation direction extracted from one misaligned fine-tune can ablate emergent misalignment across models trained on different datasets with different LoRA setups.
-
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
LLM-as-judge scoring biases concentrate in low-dimensional, type-specific activation subspaces that support bidirectional causal steering and cross-domain failure prediction.
-
Attacking Graph Foundation Models Through Their Shared Representation
A shared representation layer in graph foundation models is a distinct attack surface: input edits break three of six models and one spectral tokenizer is uniquely fragile.
-
DeFrame: Debiasing Large Language Models Against Framing Effects
LLM fairness scores shift substantially with positive vs negative framing of the same question, and DeFrame—a three-step self-revision prompt—reduces both average bias and this framing gap.
-
Sliced Transport Plans
A new sliced-Wasserstein-based discrepancy with provable semi-metric properties and a constrained Kantorovich relation, plus a generic-measure generalization of Expected Sliced plans.
-
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
ROSI bakes the refusal direction into a model's weight matrices via a rank-one update, raising refusal and jailbreak robustness with minimal measured utility cost.
-
Advertising in AI systems: Society must be vigilant
Generative AI outputs will likely carry embedded commercial content, and the paper proposes design principles, provenance tracking, and two debiasing strategies to preserve transparency.
Discussion (0). Continue with ORCID to comment.