paper:feng-how-do-language-models-bind-entities-in-2024How do language models bind entities in context?
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- ≈ 75%
- Making Large Language Models into World Models with Precondition and Effect KnowledgeIan Yang, John Gunerli, Mark Riedl Kaige Xie2024≈ 72%
- ≈ 71%
- Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event PlausibilityJennifer Hu, Ishita Dasgupta, Roma Patel, Thomas Serre, Ellie Pavlick Michael A. Lepori2026≈ 70%
- Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated ProbabilitiesSathvik Nair and Colin Phillips2026≈ 70%
- Language Agents Meet Causality -- Bridging LLMs and Causal World ModelsMatthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov John Gkountouras2024≈ 70%
- Bi-Directional Mental Model Reconciliation for Human-Robot Interaction with Large Language ModelsMichelle Zhao, Matthew B. Luebbers, Sanne Van Waveren, Reid Simmons, Henny Admoni, Sonia Chernova, and Matthew Gombolay Nina Moorman2025≈ 70%
- Multi-Agent Language Models: Advancing Cooperation, Coordination, and AdaptationArjun Vaithilingam Sudhakar2025≈ 70%
- Learning to Model the World with LanguageYuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca Dragan Jessy Lin2024≈ 70%
- ≈ 70%
- Language Models Meet World Models: Embodied Experiences Enhance Language ModelsTianhua Tao, Yi Gu, Tianmin Shu, Zirui Wang, Zichao Yang, Zhiting Hu Jiannan Xiang2023≈ 70%
- How do Large Language Models Understand Relevance? A Mechanistic Interpretability PerspectiveJiaxin Mao, Ji-Rong Wen Qi Liu2025≈ 69%
- ≈ 69%
- Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's CapabilitiesYongyuan Li, Yang Xu Zhichen Liu2026≈ 69%
- Reasoning with Language Model is Planning with World ModelYi Gu, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, Zhiting Hu Shibo Hao2023≈ 69%
- The Same But Different: Structural Similarities and Differences in Multilingual Language ModelingQinan Yu, Matianyu Zang, Carsten Eickhoff, Ellie Pavlick Ruochen Zhang2024≈ 69%
- ≈ 65%
- ≈ 65%
- Interpreting Language Model Parametersin corpus2026≈ 64%
- ≈ 64%
- Model Alignment Searchin corpus2025≈ 63%
- ≈ 63%
- ≈ 63%
- ≈ 63%
- ≈ 62%
- ≈ 62%
- ≈ 62%
- Evaluating Language Model Character Traitsin corpus2024≈ 62%
- An association-based model of dynamic behaviourin corpus2011≈ 61%
Similar preprints — Semantic Scholar
Cited by (5)
- Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
Language models retrieve bound entities through a mixture of three mechanisms, not the positional mechanism alone, and the positional signal collapses in the middle of long entity lists. With n=20 ent
- When Models Manipulate Manifolds: The Geometry of a Counting Task
Claude 3.5 Haiku's linebreaking in fixed-width text is implemented by manipulating low-dimensional, rippled 1-D feature manifolds: character count, line width, characters remaining and next-token leng
- Addressing divergent representations from causal interventions on neural networks
Causal intervention methods central to mechanistic interpretability—including activation patching, mean-difference vector patching, Sparse Autoencoders, and Distributed Alignment Search (DAS)—systemat
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering — intervening on model activations along paths constrained to lie on a learned activation manifold M_h rather than along Euclidean linear directions — produces behavioral trajectorie
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Llama-3.1-8B solves cyclic arithmetic (e.g., "what month is six months after August?") not by performing modular addition in the period of the cyclic concept (12 for months, 7 for days of the week) as