Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
Entity-centric factual question answering involves localized MLP neurons that can be causally intervened to recover entity-consistent predictions, showing robustness to various linguistic variations but with limited universality across all entities. (0 upvotes on HuggingFace)
Published on Apr 1
Authors:
,
,
Abstract
Entity-centric factual question answering involves localized MLP neurons that can be causally intervened to recover entity-consistent predictions, showing robustness to various linguistic variations but with limited universality across all entities.
AI-generated summary
Language models can answer many entity-centric factual questions, but it remains unclear which internal mechanisms are involved in this process. We study this question across multiple language models. We localize entity-selective MLP neurons using templated prompts about each entity, and then validate them with causal interventions on PopQA-based QA examples. On a curated set of 200 entities drawn from PopQA, localized neurons concentrate in early layers. Negative ablation produces entity-specific amnesia, while controlled injection at a placeholder token improves answer retrieval relative to mean-entity and wrong-cell controls. For many entities, activating a single localized neuron is sufficient to recover entity-consistent predictions once the context is initialized, consistent with compact entity retrieval rather than purely gradual enrichment across depth. Robustness to aliases, acronyms, misspellings, and multilingual forms supports a canonicalization interpretation. The effect is strong but not universal: not every entity admits a reliable single-neuron handle, and coverage is higher for popular entities. Overall, these results identify sparse, causally actionable access points for analyzing and modulating entity-conditioned factual behavior.
View arXiv page View PDF GitHub 0 Add to collection
Get this paper in your agent:
hf papers read 2604.01404
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2604.01404 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2604.01404 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2604.01404 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
researchpaperarxiv
RightNow AI Releases AutoKernel: An Open-Source Framework that Applies an Autonomous Agent Loop to GPU Kernel Optimization for Arbitrary PyTorch Models
Writing fast GPU code is one of the most grueling specializations in machine learning engineering. Researchers from RightNow AI want to automate it entirely. The RightNow AI research team has released AutoKernel, an open-source framework that applies an autonomous LLM agent loop to GPU kernel optimization for arbitrary PyTorch models. The approach is straightforward: give [ ] The post RightNow AI Releases AutoKernel: An Open-Source Framework that Applies an Autonomous Agent Loop to GPU Kernel Optimization for Arbitrary PyTorch Models appeared first on MarkTechPost .
Simple parallel estimation of the partition ratio for Gibbs distributions
arXiv:2505.18324v2 Announce Type: replace-cross Abstract: We consider the problem of estimating the partition function $Z(\beta)=\sum_x \exp(\beta(H(x))$ of a Gibbs distribution with the Hamiltonian $H:\Omega\rightarrow\{0\}\cup[1,n]$. As shown in [Harris & Kolmogorov 2024], the log-ratio $q=\ln (Z(\beta_{\max})/Z(\beta_{\min}))$ can be estimated with accuracy $\epsilon$ using $O(\frac{q \log n}{\epsilon^2})$ calls to an oracle that produces a sample from the Gibbs distribution for parameter $\beta\in[\beta_{\min},\beta_{\max}]$. That algorithm is inherently sequential, or {\em adaptive}: the queried values of $\beta$ depend on previous samples. Recently, [Liu, Yin & Zhang 2024] developed a non-adaptive version that needs $O( q (\log^2 n) (\log q + \log \log n + \epsilon^{-2}) )$ samples.
Online Graph Coloring for $k$-Colorable Graphs
arXiv:2511.16100v2 Announce Type: replace Abstract: We study the problem of online graph coloring for $k$-colorable graphs. The best previously known deterministic algorithm uses $\widetilde{O}(n^{1-\frac{1}{k!}})$ colors for general $k$ and $\widetilde{O}(n^{5/6})$ colors for $k = 4$, both given by Kierstead in 1998. In this paper, we finally break this barrier, achieving the first major improvement in nearly three decades. Our results are summarized as follows: (1) $k \geq 5$ case. We provide a deterministic online algorithm to color $k$-colorable graphs with $\widetilde{O}(n^{1-\frac{1}{k(k-1)/2}})$ colors, significantly improving the current upper bound of $\widetilde{O}(n^{1-\frac{1}{k!}})$ colors. Our algorithm also matches the best-known bound for $k = 4$ ($\widetilde{O}(n^{5/6})$ c
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
Online Graph Coloring for $k$-Colorable Graphs
arXiv:2511.16100v2 Announce Type: replace Abstract: We study the problem of online graph coloring for $k$-colorable graphs. The best previously known deterministic algorithm uses $\widetilde{O}(n^{1-\frac{1}{k!}})$ colors for general $k$ and $\widetilde{O}(n^{5/6})$ colors for $k = 4$, both given by Kierstead in 1998. In this paper, we finally break this barrier, achieving the first major improvement in nearly three decades. Our results are summarized as follows: (1) $k \geq 5$ case. We provide a deterministic online algorithm to color $k$-colorable graphs with $\widetilde{O}(n^{1-\frac{1}{k(k-1)/2}})$ colors, significantly improving the current upper bound of $\widetilde{O}(n^{1-\frac{1}{k!}})$ colors. Our algorithm also matches the best-known bound for $k = 4$ ($\widetilde{O}(n^{5/6})$ c
Zero-Freeness of the Hard-Core Model with Bounded Connective Constant
arXiv:2604.02746v1 Announce Type: cross Abstract: We study the zero-free regions of the partition function of the hard-core model on finite graphs and their implications for the analyticity of the free energy on infinite lattices. Classically, zero-freeness results have been established up to the tree uniqueness threshold $\lambda_c(\Delta-1)$ determined by the maximum degree $\Delta$. However, for many graph classes, such as regular lattices, the connective constant $\sigma$ provides a more precise measure of structural complexity than the maximum degree. While recent approximation algorithms based on correlation decay and Markov chain Monte Carlo have successfully exploited the connective constant to improve the threshold to $\lambda_c(\sigma)$, analogous results for complex zero-freenes
Stochastic Function Certification with Correlations
arXiv:2604.02611v1 Announce Type: new Abstract: We study the Stochastic Boolean Function Certification (SBFC) problem, where we are given $n$ Bernoulli random variables $\{X_e: e \in U\}$ on a ground set $U$ of $n$ elements with joint distribution $p$, a Boolean function $f: 2^U \to \{0, 1\}$, and an (unknown) scenario $S = \{e \in U: X_e = 1\}$ of active elements sampled from $p$. We seek to probe the elements one-at-a-time to reveal if they are active until we can certify $f(S) = 1$, while minimizing the expected number of probes. Unlike most previous results that assume independence, we study correlated distributions $p$ and give approximation algorithms for several classes of functions $f$. When $f(S)$ is the indicator function for whether $S$ is the spanning set of a given matroid, ou
Non-Signaling Locality Lower Bounds for Dominating Set
arXiv:2604.02582v1 Announce Type: new Abstract: Minimum dominating set is a basic local covering problem and a core task in distributed computing. Despite extensive study, in the classic LOCAL model there exist significant gaps between known algorithms and lower bounds. Chang and Li prove an $\Omega(\log n)$-locality lower bound for a constant factor approximation, while Kuhn--Moscibroda--Wattenhofer gave an algorithm beating this bound beyond $\log \Delta$-approximation, along with a weaker lower bound for this degree-dependent setting scaling roughly with $\min\{\log \Delta/\log\log \Delta,\sqrt{\log n/\log\log n}\}$. Unfortunately, this latter bound is weak for small $\Delta$, and never recovers the Chang--Li bound, leaving central questions: does $O(\log \Delta)$-approximation require
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!