LLM Grounding

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 127% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 216

All topics

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
Nov 3, 2025Sekh Mainul Islam, Pepa Atanasova, Isabelle AugensteinDisentangled Representation Learning LLM Grounding
University of Copenhagen
BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction
Oct 18, 2025Tian Xia, Tianrun Gao, Wenhao Deng +4LLM Evaluation LLM Grounding
Westlake University, China · Uniforce AI, China
Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs
May 24, 2025Chen Yang, Ruping Xu, Ruizhe Li +2LLM Grounding LLM Prompting
Zhejiang University of Technology, China1 · Zhejiang Key Laboratory of Visual Information Intelligent Processing, China 2 · University of Aberdeen, UK +1
Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family
Apr 25, 2025Pierre-Carl Langlais, Pavel Chizhov, Mattia Nee +6Retrieval-Augmented Generation LLM Grounding
PleIAs, Paris, France
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Mar 3, 2025Tin Nguyen, Logan Bolton, Mohammad Reza Taesiri +2LLM Grounding LLM Answer Verification
Auburn University · University of Alberta
Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization
Date pendingShuo GuanLLM Grounding Text Summarization
UBS AG NY, 10010

Nov 3, 2025, cs.CLJ/K move · Enter open · S save

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein

University of Copenhagen

Disentangled Representation Learning LLM Grounding Knowledge Conflicts in Language Models Factual Knowledge in Language Models

Open paper AskPDF arXiv

Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions by drawing on external Context Knowledge (CK) and Parametric Knowledge (PK). Understanding the interaction between these sources is key to assessing NLE grounding, yet these dynamics remain underexplored. Prior work has largely focused on i) single-step generation and ii) modeled PK--CK interaction as a binary choice within a rank-1 subspace. This approach overlooks richer interactions and how they unfold over longer generations, such as complementary or supportive knowledge. We propose a novel rank-2 projection subspace that disentangles PK and CK contributions more accurately and use it for the first multi-step analysis of knowledge interactions across longer NLE sequences. Experiments across four QA datasets and three open-weight LLMs demonstrate that rank-1 subspaces struggle to represent diverse interactions, whereas our rank-2 formulation captures them effectively, highlighting PK alignment for supportive interactions and CK alignment for conflicting ones. Our multi-step analysis reveals that hallucinated generations exhibit strong alignment with the PK direction, though context-faithful generations maintain a more balanced alignment between PK and CK.

Momentum

Related topics

Latest papers 216

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction

Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization