Related papers: Steering Knowledge Selection Behaviours in LLMs vi…

Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via…

In recent years, unlearning techniques, which are methods for inducing a model to "forget" previously learned information, have attracted attention as a way to address privacy and copyright concerns in large language models (LLMs) and large…

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

In recent years, large language models (LLMs) have spurred a new research paradigm in natural language processing. Despite their excellent capability in knowledge-based question answering and reasoning, their potential to retain faulty or…

Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its…

While large language models (LLMs) perform strongly on diverse tasks, their trustworthiness is limited by erratic behavior that is unfaithful to their internal knowledge. In particular, LLMs often fail on multiple-choice questions (MCQs)…

Large language models (LLMs) demonstrate the capacity to reconstruct and trace learned content from their training data under specific elicitation conditions, yet this capability does not manifest in standard generation contexts. This…

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…

Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual knowledge (CK) and parametric knowledge (PK) disagree or are…

Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks,…

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

In this paper, we explore the potential of Large Language Models (LLMs) with assertions to mitigate imbalances in educational datasets. Traditional models often fall short in such contexts, particularly due to the complexity and nuanced…

Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal…

As large language models (LLMs) are increasingly adopted in safety-critical and regulated sectors, the retention of sensitive or prohibited knowledge introduces escalating risks, ranging from privacy leakage to regulatory non-compliance to…

Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions or emergent misaligned tendencies. Model diffing addresses…

Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent…

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

The exponential growth of scientific literature challenges researchers extracting and synthesizing knowledge. Traditional search engines return many sources without direct, detailed answers, while general-purpose LLMs may offer concise…

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT)…

Calibration measures whether a model's predicted confidence aligns with its empirical accuracy, and is central to the reliable deployment of large language models (LLMs) in high-stakes domains such as medicine and law. While much recent…