Unmixing Mechanisms: How Language Models Choose Among Binding Strategies

Background and motivation A growing body of work has shown that language models (LMs) use abstract positional information to perform variable binding, that is, to associate entities with their attributes in context and retrieve them later [1, 2]. Recent work by Gur-Arieh et al. (2025) [3] demonstrated that the positional mechanism is not the whole story: LMs also employ lexical and reflexive mechanisms to solve binding tasks, and these become increasingly important as the context grows longer.

Our understanding of how these mechanisms interact, however, remains limited. In particular, we do not yet know why the positional mechanism degrades in longer contexts, or what determines when the other mechanisms take over. Two hypotheses seem plausible. Under a backup hypothesis, positional information is simply absent or unreliable for certain entity–attribute pairs, and the lexical and reflexive mechanisms step in to compensate at a later stage of the final token computation. Under a competition hypothesis, multiple mechanisms are simultaneously active at the final token position and compete to drive the model's output, with the positional mechanism prevailing in some instances and losing out in others.

Preliminary findings and proposed work My initial explorations with Llama-3.1-8B-Instruct indicate that the same set of attention heads at the final token position is responsible for fetching both positional and lexical information, which provides initial support for the competition hypothesis. Establishing this rigorously, however, requires a more systematic investigation of what these heads read and write across a wide range of entity–attribute pairs. Do they always write both types of information, differing only in relative strength, or do they write just one of them depending on the pair? And do they write these signals into a shared subspace or into distinct ones?

Beyond characterizing the mechanisms' interplay, I plan to pursue two further directions. First, I suspect that the degradation of the positional mechanism in long contexts is connected to properties of rotary position embeddings, a link that has not yet been studied systematically. Second, if time and resources permit, I aim to examine the training dynamics of these mechanisms: which properties of the training data give rise to each mechanism, and at what stage of training does each one emerge?

Expected outcome A detailed mechanistic account of why, when, and how LMs recruit each binding mechanism, resolving whether the mechanisms act as backups or competitors, clarifying how positional encoding choices shape binding reliability at long context lengths, and potentially tracing how these mechanisms emerge during training. Because binding is a core primitive of in-context reasoning, and binding failures are a plausible source of long-context errors, this understanding would inform both interpretability research and efforts to make LMs more reliable over long inputs.

[1] - Prakash et al, "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking", 2024. [2] - Prakash et al, "Language Models use Lookbacks to Track Beliefs", 2025. [3] - Gur-Arieh et al, "Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context", 2025.

Overseeing advanced AI systems requires understanding the computations they perform internally, and variable binding is among the most fundamental. Binding is the canonical operation of symbolic thought, and how neural networks implement it sits at the center of the debate over whether modern AI systems achieve genuinely structured, systematic reasoning [1]. It underlies entity tracking, state tracking, theory of mind, and the ability to correctly attribute claims, beliefs, and instructions to their sources. It is also a documented bottleneck in frontier systems: many puzzling failures of state-of-the-art vision-language models on multi-object reasoning have been traced to the binding problem [2], and in text LMs, binding degrades over long contexts, producing confident misattributions. As LMs are deployed as long-horizon agents juggling many entities, users, tools, and instruction sources, misbinding becomes a safety problem: an agent that conflates who asserted or requested what can be manipulated or fail silently.

My long-term research agenda is to develop causal models of binding that help us understand how deployed LMs succeed or fail at it. My prior work has taken first steps on this agenda: Prakash et al. (2024) showed that LMs use an abstract positional mechanism for entity-tracking, and Prakash et al. (2025) identified a generic computation unit called the lookback mechanism LMs use to track beliefs in context. I see this project as the natural next step: extending our mechanistic understanding of binding to longer contexts, taking our understanding closer to the regime where deployed models actually operate.

[1] Griffiths et al, "Whither symbols in the era of advanced neural networks?", 2025. [2] Campbell et al, "Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem", 2024.

I expect the mentee to take the lead on this project and work fairly autonomously. While I'll be available for guidance and support throughout, the mentee should drive the research, formulating well-motivated hypotheses and implementing experiments to test them. I'm therefore looking for someone who is genuinely curious about how LMs work and has some intuitions about their internal mechanisms. Please also mention in your application whether you would be open to working with another mentee on this project.

• Highly proficient in Python and PyTorch; you'll be implementing and debugging your own experiments fairly independently.
• Completed at least one hands-on mechanistic interpretability investigation using a library such as nnsight, TransformerLens, or pyvene (self-directed projects, paper replications, and ARENA-style coursework all count).
• Familiar with common mechanistic interpretability methods such as the logit lens, activation patching, and distributed alignment search (DAS).
• Comfortable with core linear algebra concepts, matrices, vector spaces and subspaces, basis vectors, rank, as analyzing the subspaces that attention heads read from and write to is central to this project.