From the 2 of 15 linked papers with an AI index.
15 papers
Steering Instruction Hierarchies at Inference Time
Siqi Zeng, Sewoong Lee, Han Zhao +1
The paper proposes V‑Steer, a training‑free method that modifies cached value vectors during inference to ensure higher‑priority prompts (like system prompts) override lower‑priori…
Scaling Evaluation-time Compute with Reasoning Models as Evaluators
Seungone Kim, Ian Wu, Jinu Lee +8
The paper studies how using larger, chain‑of‑thought reasoning language models as evaluators—by allocating more test‑time compute—can improve the accuracy of evaluating and reranki…
ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
Jinu Lee, Shivam Agarwal, Amruta Parulekar +3
Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the re…
SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
Yekaterina Yegorova, Argyrios Gerogiannis, Haolong Zheng +3
Speech-aware large language models often generalize poorly to out-of-domain settings. We propose SALSA (Speech-Aware LLM Adaptation via Learned Steering Activations), a lightweight…
Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics
Jinu Lee, Kyoung-Woon On, Simeng Han +2
Evaluating the quality of LLM-generated reasoning traces in expert domains (e.g., law) is essential for ensuring credibility and explainability, yet remains challenging due to the…
Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures
Risham Sidhu, Julia Hockenmaier
We introduce GSU, a text-only grid dataset to evaluate the spatial reasoning capabilities of LLMs over 3 core tasks: navigation, object localization, and structure composition. By…