Sep 2026· Proceedings of the 35th ACM International Conference on Information and Knowledge Management· 0 citations· 24 references
Computer Science
TL;DR
Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline.
Abstract
Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify progress, and stop. We study whether trajectory fine-tuning can improve small language models (SLMs) as next-action controllers. We additionally evaluate a low-resource setting in which a single SLM serves as both the controller and the final-answer generator. From accepted teacher search traces, we build a seven-way action-prediction task, where the model predicts the next structured teacher action from the current trajectory state, and evaluate LoRA-supervised fine-tuning across SLMs and xSLMs as controllers. On 1,646 held-out action examples, Granite 4.1 3B trained on 13,194 actions reaches macro-F1 0.6536, compared with 0.1736 for zero-shot prompting of the same model and 0.5399 for a TF-IDF logistic-regression baseline. In an end-to-end controller/generator swap evaluation over 149 held-out trajectories, using the fine-tuned model for both roles improves Exact Match from 0.7530 to 0.7946 and token F1 from 0.7783 to 0.8295 compared with using the base model as both controller and generator. The cross-role conditions show that the fine-tuned controller increases evidence-fact recording when the generator is fixed, while controller-only final-answer gains are not statistically clear. Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline. The code used in this paper is publicly available.
Q-CueGraph maps a question and an image representation to budgeted, coordinate-level observations for a frozen reader, and reaches 92% of full-image ANLS on InfographicVQA from about half the image area.
The Selection--Realization Hypothesis is proposed, which views demonstrations as inducing a compact family of internal changes from which the query selects, while the model's computation constrains how the selected change can be implemented.
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-shot OPD keeps impro...
This work evaluates the curated store with a test set, on two contamination-free benchmarks: KBGym, a fictional-universe generator the authors release, and PhantomWiki, a fictional-universe generator they release, and PhantomWiki, a fictional-universe generator they release.
In-context learning (ICL) is crucial for boosting the inference performance of large language models (LLMs). However, the effectiveness of ICL in LLMs is greatly influenced by the choice of demonstration sets. Exhaustive searches over these sets are combinatorial, and existing selectors often rely on relevance or likel...
Query understanding (QU) in production search systems has typically relied on separate models for each subtask, such as search intent classification, attribute extraction, and query rewriting. Large language models (LLMs) now make it possible to consolidate these subtasks into a single model that emits a unified QU out...