Direct Preference Optimization Using Sparse Feature-Level Constraints

The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved notable success, they often introduce computational inefficiencies and training instability. In this paper, we propose Feature-level constrained Preference Optimization (FPO), a novel method designed to simplify the alignment process while ensuring stability. FPO leverages pre-trained Sparse Autoencoders (SAEs) and introduces feature-level constraints, allowing for efficient, sparsity-enforced alignment. Our approach enjoys efficiency by using sparse features activated in a well-trained sparse autoencoder and the quality of sequential KL divergence by using the feature-level offline reference. Experimental results on benchmark datasets demonstrate that FPO achieves a 5.08% absolute improvement in win rate with much lower computational cost compared to state-of-the-art baselines, making it a promising solution for efficient and controllable LLM alignments.

Subtle Errors Matter: Preference Learning via Error-injected Self-editing

Large Language Models (LLMs) have exhibited strong mathematical reasoning and computational prowess, tackling tasks ranging from basic arithmetic to advanced competition-level problems. However, frequently occurring subtle errors, such as miscalculations or incorrect substitutions, limit the models' full mathematical potential. Existing studies to improve mathematical ability typically involve distilling reasoning skills from stronger LLMs or applying preference learning to step-wise response pairs. Although these methods leverage samples of varying granularity to mitigate reasoning errors, they overlook the frequently occurring subtle errors. A major reason is that sampled preference pairs involve differences unrelated to the errors, which may distract the model from focusing on subtle errors. In this work, we propose a novel preference learning framework called eRror-Injected Self-Editing (RISE), which injects predefined subtle errors into partial tokens of correct solutions to construct hard pairs for error mitigation. In detail, RISE uses the model itself to edit a small number of tokens in the solution, injecting designed subtle errors. Then, pairs composed of self-edited solutions and their corresponding correct ones, along with pairs of correct and incorrect solutions obtained through sampling, are used together for subtle error-aware DPO training. Compared with other preference learning methods, RISE further refines the training objective to focus on predefined errors and their tokens, without requiring fine-grained sampling or preference annotation. Extensive experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH.

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning

Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surpass ICL given sufficient training samples as it allows the model to adjust its internal parameters based on the data. However, this paper presents a counterintuitive finding: For tasks with implicit patterns, ICL captures these patterns significantly better than fine-tuning. We developed several datasets featuring implicit patterns, such as sequences determining answers through parity or identifying reducible terms in calculations. We then evaluated the models' understanding of these patterns under both fine-tuning and ICL across models ranging from 0.5B to 7B parameters. The results indicate that models employing ICL can quickly grasp deep patterns and significantly improve accuracy. In contrast, fine-tuning, despite utilizing thousands of times more training samples than ICL, achieved only limited improvements. We also proposed circuit shift theory from a mechanistic interpretability's view to explain why ICL wins.

E2CL: Exploration-based Error Correction Learning for Embodied Agents

Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental knowledge, leading to infeasible actions. Traditional environment alignment methods, such as supervised learning on expert trajectories and reinforcement learning, face limitations in covering environmental knowledge and achieving efficient convergence, respectively. Inspired by human learning, we propose Exploration-based Error Correction Learning (E2CL), a novel framework that leverages exploration-induced errors and environmental feedback to enhance environment alignment for LM-based agents. E2CL incorporates teacher-guided and teacher-free exploration to gather environmental feedback and correct erroneous actions. The agent learns to provide feedback and self-correct, thereby enhancing its adaptability to target environments. Evaluations in the Virtualhome environment demonstrate that E2CL-trained agents outperform those trained by baseline methods and exhibit superior self-correction capabilities.

Evolving to be Your Soulmate: Personalized Dialogue Agents with Dynamically Adapted Personas

Previous research on persona-based dialogue agents typically preset the agent's persona before deployment, which remains static thereafter. In this paper, we take a step further and explore a new paradigm called Self-evolving Personalized Dialogue Agents (SPDA), where the agent continuously evolves during the conversation to better align with the user's anticipation by dynamically adapting its persona. This paradigm could enable better personalization for each user, but also introduce unique challenges, which mainly lie in the process of persona adaptation. Two key issues include how to achieve persona alignment with the user and how to ensure smooth transition in the adaptation process. To address them, we propose a novel framework that refines the persona at hierarchical levels to progressively align better with the user in a controllable way. Experiments show that integrating the personas adapted by our framework consistently enhances personalization and overall dialogue performance across various base systems.

No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation results. However, the attack mechanisms of these strategies are still underexplored. In this paper, we ask the following question: \textit{while these approaches can all significantly compromise safety, do their attack mechanisms exhibit strong similarities?} To answer this question, we break down the safeguarding process of an LLM when encountered with harmful instructions into three stages: (1) recognizing harmful instructions, (2) generating an initial refusing tone, and (3) completing the refusal response. Accordingly, we investigate whether and how different attack strategies could influence each stage of this safeguarding process. We utilize techniques such as logit lens and activation patching to identify model components that drive specific behavior, and we apply cross-model probing to examine representation shifts after an attack. In particular, we analyze the two most representative types of attack approaches: Explicit Harmful Attack (EHA) and Identity-Shifting Attack (ISA). Surprisingly, we find that their attack mechanisms diverge dramatically. Unlike ISA, EHA tends to aggressively target the harmful recognition stage. While both EHA and ISA disrupt the latter two stages, the extent and mechanisms of their attacks differ significantly. Our findings underscore the importance of understanding LLMs' internal safeguarding process and suggest that diverse defense mechanisms are required to effectively cope with various types of attacks.

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue

Tuning pretrained language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role disparities between two speakers and the multi-round interactive process that dialogues ought to be. Such a manner leads to unsatisfactory chat consistency of the built agent. In this work, we emphasize the interactive, communicative nature of dialogue and argue that it is more feasible to model the speaker roles of agent and user separately, enabling the agent to adhere to its role consistently. We propose an efficient Multi-round Interactive Dialogue Tuning (Midi-Tuning) framework. It models the agent and user individually with two adapters built upon large language models, where they utilize utterances round by round in alternating order and are tuned via a round-level memory caching mechanism. Extensive experiments demonstrate that, our framework performs superior to traditional fine-tuning and harbors the tremendous potential for improving dialogue consistency.

Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback

An emotional support conversation system aims to alleviate users' emotional distress and assist them in addressing their challenges. To generate supportive responses, it is critical to consider multiple factors such as empathy, support strategies, and response coherence, as established in prior methods. Nonetheless, previous models occasionally generate unhelpful responses, which intend to provide support but display counterproductive effects. According to psychology and communication theories, poor performance in just one contributing factor might cause a response to be unhelpful. From the model training perspective, since these models have not been exposed to unhelpful responses during their training phase, they are unable to distinguish if the tokens they generate might result in unhelpful responses during inference. To address this issue, we introduce a novel model-agnostic framework named mitigating unhelpfulness with multifaceted AI feedback for emotional support (Muffin). Specifically, Muffin employs a multifaceted AI feedback module to assess the helpfulness of responses generated by a specific model with consideration of multiple factors. Using contrastive learning, it then reduces the likelihood of the model generating unhelpful responses compared to the helpful ones. Experimental results demonstrate that Muffin effectively mitigates the generation of unhelpful responses while slightly increasing response fluency and relevance.

COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal

In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems. Apart from the requirement for much more sophisticated strategic reasoning and communication skills, a significant challenge of these tasks lies in the difficulty of objectively measuring the achievement of their goals in a quantifiable way, making it difficult for existing research to directly optimize the dialogue procedure towards them. In our work, we emphasize the multifaceted nature of complex dialogue goals and argue that it is more feasible to accomplish them by comprehensively considering and jointly promoting their different aspects. To this end, we propose a novel dialogue framework, Cooper, which coordinates multiple specialized agents, each dedicated to a specific dialogue goal aspect separately, to approach the complex objective. Through this divide-and-conquer manner, we make complex dialogue goals more approachable and elicit greater intelligence via the collaboration of individual agents. Experiments on persuasion and emotional support dialogues demonstrate the superiority of our method over a set of competitive baselines.

Self-Detoxifying Language Models via Toxification Reversal

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and decoding-based. However, the former is often resource-intensive, while the latter relies on additional components and potentially compromises the generation fluency. In this paper, we propose a more lightweight approach that enables the PLM itself to achieve "self-detoxification". Our method is built upon the observation that prepending a negative steering prompt can effectively induce PLMs to generate toxic content. At the same time, we are inspired by the recent research in the interpretability field, which formulates the evolving contextualized representations within the PLM as an information stream facilitated by the attention layers. Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers. Experimental results show that our approach, without any fine-tuning or extra components, can achieve comparable performance with state-of-the-art methods.