DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls

Ajit Mallavarapu; Ziwei Gu

Home/Archive/arXiv

arXiv · 2610.04174

DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls

Ajit Mallavarapu·Ziwei Gu

View original source ↗Read source document ↗Export metadata ↓

Abstract

Large language model writing interfaces often make users steer outputs by repeatedly articulating desired changes in natural language. Yet writers may recognize useful stylistic directions only after seeing alternatives, making revision recall-heavy. We present DimSteer, an authoring interface that samples prompt-local completions, discovers high-variance activation-space axes of variation, labels them, and exposes them as sliders with pole previews, diff comparison, and reset controls. Users can manipulate discovered dimensions, reducing the need to reformulate prompts for each stylistic adjustment. In a within-subjects study with 16 participants against a matched prompt-only baseline, DimSteer reduced mental demand, effort, and frustration while preserving comparable perceived success. Participants valued the surfaced dimensions, yet 15 of 16 disagreed that they would have thought to request the same changes in a prompt. Results suggest prompt-local controls can shift LLM authoring from recall-based prompting toward recognition-based exploration and direct manipulation, while preserving prompting for open-ended edits.

Explore related subjects

cs.HC cs.CL

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Ajit Mallavarapu, Ziwei Gu. 2026-10-03. DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls. https://arxiv.org/abs/2610.04174

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

CHOMP: Multimodal Chewing Side Detection with Earphones

Chewing-side preference (CSP) is a risk factor for temporomandibular disorders (TMDs) and a behavioral manifestation. Although TMDs affect roughly one-third of the global population, assessment relies on clinical examinations and self-reports, providing limited insight into everyday jaw function. We present CHOMP, the first earphone-based chewing-side detection system for continuous CSP monitoring. Using OpenEarable 2.0, we collected multimodal data from 20 participants with microphones, a bone-conduction microphone, IMU, PPG, and a pressure sensor across diverse foods, activities, and acoustic-interference conditions. CHOMP models paired-ear temporal feature sequences using modality-specific bidirectional GRUs, multimodal fusion, and prototype-based classification with an optional short user adaptation. Microphones achieve the strongest single-sensor performance, with median macro F1 scores of 97.2% under leave-one-food-out (LOFO) and 95.7% under leave-one-subject-out (LOSO) evaluation after user adaptation. Multimodal fusion reaches 98.0% under LOFO and 97.3% under adapted LOSO. We demonstrate CHOMP's performance under three acoustic-interference conditions and within a cafeteria setting. Our results establish earphones as a practical platform for everyday CSP monitoring and jaw-function assessment.

cs.HC↗

arXiv2026

How Children Design and Reason about Trustworthy AI Chatbots

Children increasingly interact with AI chatbots, making trust calibration essential to AI literacy. Prior research has examined children's trust in AI mainly as users evaluating systems built by others, rather than as designers of their own chatbots. We developed a chatbot-building environment with adjustable trust-relevant traits (e.g., confidence, transparency, formality, assertiveness), rules, and persona. We conducted mixed-methods study with 115 learners (ages 8-18) who made 119 chatbots. We examined how children configured their chatbots, reasoned about trustworthiness, and how closely chatbot behavior aligned with their designs. Younger students (age 10-13) set significantly higher confidence than older students (age 14-18), and some deliberately built chatbots that gave wrong answers on purpose, yet still called them trustworthy, arguing that a chatbot does what it was built to do. Younger students equated trust with purpose-fulfillment, while older students linked it to transparent, calibrated design. Students also calibrated academic chatbots to be more transparent and formal than hobby chatbots. We identify seven design dimensions describing what children believe makes a chatbot trustworthy, and discuss implications for AI literacy tools.

cs.HC↗

arXiv2026

LeanSide: A Formally Verified Co-Reasoning System for Natural-language Proofs

Large language models are increasingly used as collaborators on deductive-reasoning tasks, but their outputs can hallucinate or pull users away from intended reasoning. Formal proof assistants provide machine-checked verification, but have a steep learning curve and require more granular reasoning than human written proofs. We explore an interface that combines these strengths, allowing users to write and revise free-form natural-language proofs while a verified backend checks their reasoning and returns feedback at the user's granularity. We study this interface in the context of undergraduate mathematics education by developing LeanSide, a formally verified co-reasoning system, which auto-formalizes student reasoning into Lean and informalizes verifier output into understandable feedback. We conducted user studies through classroom deployment and analyzed which system properties helped students make progress and which caused them to get stuck. We use these findings to derive design implications for using a formally verified backend in human-AI co-reasoning systems.

cs.HC↗