5 papers
From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models
Tianda Sun, Dimitar Kazakov
Activation interventions can make a language model produce a target answer, but can the model use the intended condition in other computations? We study this question in Qwen3.5-27…
Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams
Tianda Sun, Dimitar Kazakov
Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is r…
Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use
Tianda Sun, Dimitar Kazakov
We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation verbs over Complex WebQuest…
Kinship Data Benchmark for Multi-hop Reasoning
Tianda Sun, Dimitar Kazakov
Multi-hop kinship reasoning is a natural testbed for LLM compositionality, but existing benchmarks (notably CLUTRR) cover only the descriptive Eskimo system. We introduce KinshipQA…
Learning Fairer Representations with FairVIC
Charmaine Barker, Daniel Bethell, Dimitar Kazakov
Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases,…