Related papers: When to Trust Context: Self-Reflective Debates for…

Long-term memory systems enable conversational agents based on large language models (LLMs) to retain, retrieve, and apply user-specific information across multi-session interactions. However, existing evaluations mainly assess…

Understanding the internal thinking process of Large Language Models (LLMs) and the cause of hallucinations remains a key challenge. To this end, we introduce latent debate, a novel framework for interpreting model predictions through the…

Language models (LMs) are increasingly being integrated into a wide range of applications, yet the modern evaluation paradigm does not sufficiently reflect how they are actually being used. Current evaluations rely on benchmarks that often…

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only…

We present R-Debater, an agentic framework for generating multi-turn debates built on argumentative memory. Grounded in rhetoric and memory studies, the system views debate as a process of recalling and adapting prior arguments to maintain…

Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasized mid-context degradation in question answering, this…

To promote constructive discussion of controversial topics online, we propose automatic reframing of disagreeing responses to signal receptiveness to a preceding comment. Drawing on research from psychology, communications, and linguistics,…

Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where user goals and conversational context persist and evolve. A…

Conversational recommender systems aim to provide personalized recommendations by analyzing and utilizing contextual information related to dialogue. However, existing methods typically model the dialogue context as a whole, neglecting the…

We present a novel model for the problem of ranking a collection of documents according to their semantic similarity to a source (query) document. While the problem of document-to-document similarity ranking has been studied, most modern…

We study the source of uncertainty in DeepSeek R1-32B by analyzing its self-reported verbal confidence on question answering (QA) tasks. In the default answer-then-confidence setting, the model is regularly over-confident, whereas semantic…

Super-resolution (SR) is an ill-posed inverse problem with a large set of feasible solutions that are consistent with a given low-resolution image. Various deterministic algorithms aim to find a single solution that balances fidelity and…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Prior approaches to realizing mixed-initiative human--computer referential communication have adopted information-state or collaborative problem-solving approaches. In this paper, we argue for a new approach, inspired by coherence-based…

Mental health disorders impose a substantial global socioeconomic burden. While large language models (LLMs) offer 24/7, non-judgmental interactions to address this gap, pretrained models lack contextual coherence and emotional alignment…

Large language models internalize enormous parametric knowledge during pre-training. Concurrently, realistic applications necessitate external contextual knowledge to aid models on the underlying tasks. This raises a crucial dilemma known…

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…

Retrieval-Augmented Generation (RAG) grounds language models in factual evidence but introduces critical challenges regarding knowledge conflicts between internalized parameters and retrieved information. However, existing reliability…

As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely…

Fact-checking research has extensively explored verification but less so the generation of natural-language explanations, crucial for user trust. While Large Language Models (LLMs) excel in text generation, their capability for producing…