Related papers: Contrastive Reasoning Alignment: Reinforcement Lea…
Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…
Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…
Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces…
While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…
Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent reasoning benefit…
Reinforcement learning (RL) enables robots to operate in uncertain environments, but standard approaches often struggle with poor generalization to unseen tasks. Context-adaptive meta reinforcement learning addresses these limitations by…
Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…
Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while unconstrained RFT achieves strong reasoning performance, it…
The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexical similarity. The contrastive learning paradigm is…
Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existing post-training paradigms exhibit fundamental trade-offs:…
LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sample. A natural approach would be to provide ground-truth…
Reasoning capability plays a significantly critical role in the the broad applications of Large Language Models (LLMs). To enhance the reasoning performance of LLMs, diverse Reinforcement Learning (RL)-based fine-tuning approaches have been…
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…
Representation Fine-tuning (ReFT), a recently proposed Parameter-Efficient Fine-Tuning (PEFT) method, has attracted widespread attention for significantly improving parameter efficiency by editing representation space alone. In this work,…
As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning…
In this paper, we introduce a novel neural network training framework that increases model's adversarial robustness to adversarial attacks while maintaining high clean accuracy by combining contrastive learning (CL) with adversarial…
Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…
Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…
Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…
Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limiting effectiveness and transferability. We…