Papers by Scott Sanner

13 papers
Verifiable, Debuggable, and Repairable Commonsense Logical Reasoning via LLM-based Theory Resolution (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have led to substantial interest in their application to commonsense reasoning tasks.
Approach: They propose a logical reasoning framework that integrates commonsense knowledge with a verifiable logical framework that mitigates hallucinations and facilitates debugging.
Outcome: The proposed framework improves on three language-based reasoning tasks and improves accuracy and reasoning correctness.
COUNT: COntrastive UNlikelihood Text Style Transfer for Text Detoxification (2023.findings-emnlp)

Copied to clipboard

Challenge: Text detoxification is a task to ensure the generation of non-toxic and safe text.
Approach: They propose a novel contrastive unlikelihood objective that combines rephrasing and identity mapping to effectively isolate and focus learning on non-toxic style transfer.
Outcome: The proposed method achieves significant improvements in fluency, content preservation, and detoxification on two parallel datasets.
Semantic XPath: Structured Agentic Memory Access for Conversational AI (2026.acl-demo)

Copied to clipboard

Challenge: Early ConvAI agents rely on an in-context approach that appends the growing conversation history to the model input, but this approach scales poorly under context-window limits.
Approach: They propose a tree-structured memory module to access and update structured conversational memory.
Outcome: The proposed system improves over flat-RAG baselines while using only 9.1% of the tokens required by in-context memory.
Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparison (2025.findings-acl)

Copied to clipboard

Challenge: Existing contrastive summarization methods such as STRUM-LLM fail to clarify differences between items . emergence of large language models (LLMs) has revolutionized QCS capabilities .
Approach: They propose a new method that generates focused and contrastive summaries by using debate-style prompting.
Outcome: Experiments show that Q-STRUM Debate performs better than existing methods on key contrastive summarization criteria.
DiffuDetox: A Mixed Diffusion Model for Text Detoxification (2023.findings-acl)

Copied to clipboard

Challenge: Existing text generation models that reduce toxicity of toxic text are inadequate for text detoxification tasks.
Approach: They propose a conditional and unconditional diffusion model for text detoxification . conditional model takes toxic text as condition and reduces its toxicity . experimental results show the model achieves human-level fluency .
Outcome: The proposed model reduces toxic text and produces diverse sentences . it can be used to train other models and ensure fluency .
Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches passively rely on first-stage dense retrievers, which leads to two limitations: failing to retrieve relevant passages in semantically distinct clusters and failing to propagate relevance signals to the broader corpus.
Approach: They propose a framework that propagates sparse LLM relevance signals across the embedding space to guide global exploration.
Outcome: Experiments show that the proposed framework outperforms existing approaches under the same budget on all four datasets.
Open-World Planning via Lifted Regression with LLM-Inferred Affordances for Embodied Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing open-world planning methods rely on closed-world assumption (CWA) symbolic planners face combinatorial explosion of states and actions due to reliance on grounding.
Approach: They propose an open-world planning approach integrating lifted regression with LLM-generated affordances.
Outcome: The proposed approach outperforms state-of-the-art LLM planners and a grounded planner on three benchmarks.
Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for evaluating item labels fail to leverage scenario-specific information modalities, present redundant information that is visually inferable, and lack latent awareness of users' information needs.
Approach: They propose a principled categorization of information needs into explicit intent satisfaction and proactive information needs and define evaluation metrics for item label selection.
Outcome: The proposed evaluation framework is based on IR-, LLM-, and VLM-based methods across fashion, movie recommendation, and retail shopping scenarios.
Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing Knowledge Graph Question Answering (KGQA) methods focus on answering factual questions, leaving questions involving commonsense reasoning unaddressed.
Approach: They propose a commonsense KGQA methodology that axiomatically surfaces commonsensical knowledge of Large Language Models and grounding every factual reasoning step on KG triples.
Outcome: The proposed method outperforms existing methods and reduces instances of hallucination and reasoning errors.
Gaussian Process Optimization for Adaptable Multi-Objective Text Generation using Linearly-Weighted Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Multi-objective text generation requires a method to optimize for dynamic requirements of the overall objective.
Approach: They propose a linear combination of objective-specific language models to efficiently adapt the decoding process and optimize for the desired overall objective without retraining one or more language models.
Outcome: The proposed method outperforms other weighting schemes and standard baselines in a few iterations of decoding.
Batched Self-Consistency Improves LLM Relevance Assessment and Ranking (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work has focused on a one-by-one pointwise (PW) scoring strategy where each LLM call judges one passage at a time against the query.
Approach: They propose to use batched PW methods to evaluate multiple passages per LLM call to improve efficiency and judgment quality by enabling content from multiple passage to be seen jointly.
Outcome: The proposed methods improve efficiency and judgment quality by enabling content from multiple passages to be seen jointly.
MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Empirical evidence suggests that manifold-aware distance allows DPR to leverage context from related neighboring passages.
Approach: They propose a "manifold-aware" distance metric that measures query–passage distance . they propose to model the intrinsic manifold structure of passages using a nearest-neighbor graph .
Outcome: Empirical evidence suggests MA-DPR outperforms Euclidean and cosine distances on OOD . it can be applied to a wide range of dense embedding and retrieval tasks .
Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgments (2026.findings-acl)

Copied to clipboard

Challenge: Existing NLRec approaches use Dense Retrieval to compute item relevance scores . DR views the request as the sole relevance label, leading to a weak proxy for query relevance.
Approach: They propose to use Gaussian Process Regression to model item relevance . they propose to combine LLM with a Gauss-based kernel to model multimodal relevance judging .
Outcome: The proposed approach outperforms simpler unimodal kernels and baseline methods by up to 65% on four NLRec datasets and two LLM backbones.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations