Related papers: Auditing Reasoning-Trace Memorization Claims after…

Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep thinking. However, we identify a phenomenon we term…

Large language models (LLMs) have transformed sentiment analysis, yet balancing accuracy, efficiency, and explainability remains a critical challenge. This study presents the first comprehensive evaluation of DeepSeek-R1--an open-source…

Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities. In recent years, large-scale pre-trained language models have shown remarkable memorizing ability. On the…

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…

Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting…

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Recent advances in reasoning-focused Large Language Models (LLMs) have introduced Chain-of-Thought (CoT) traces - intermediate reasoning steps generated before a final answer. These traces, as in DeepSeek R1, guide inference and train…

Conformal unlearning aims to ensure that a trained conformal predictor miscovers data points with specific shared characteristics, such as those from a particular label class, associated with a specific user, or belonging to a defined…

Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel. However, these…

We study learned memory tokens as a computational scratchpad for a single-block Universal Transformer with Adaptive Computation Time (ACT) on Sudoku-Extreme, a combinatorial reasoning benchmark. Memory tokens are empirically necessary: no…

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in…

RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d.\ sampling budget from $k{=}32$ to $k{=}64$ produces zero additional solved theorems (42/244 in both cases). A…

Certified machine unlearning aims to provably remove the influence of a deletion set $U$ from a model trained on a dataset $S$, by producing an unlearned output that is statistically indistinguishable from retraining on the retain set…

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…

Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text tokens. However, this results in lengthy inputs where many words…

Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap, performing better in high-resource languages than in low-resource ones. While recent efforts have…

Retrieval-augmented generation (RAG) has become a powerful framework for enhancing large language models in knowledge-intensive and reasoning tasks. However, as reasoning chains deepen or search trees expand, RAG systems often face two…

Prior work has shown that a significant driver of performance in reasoning models is their ability to reason and self-correct. A distinctive marker in these reasoning traces is the token wait, which often signals reasoning behavior such as…

Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but runs the risk of producing post-hoc rationalizations: when models can see the answer during generation, the answer serves as a cognitive…