--- title: 'CESRec: Conversational Sequential Recommendation' url: https://www.emergentmind.com/topics/cesrec type: topic --- # CESRec: Conversational Sequential Recommendation Searching arXiv for CESRec and closely related recommendation papers to ground the article. arxiv_search query: 2509.09342 CESRec sequential recommendation conversational feedback CESRec, short for **Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback**, is a framework for integrating **sequential recommendation systems (SRS)** and **conversational recommendation systems (CRS)** by using conversational feedback to rewrite a user’s historical interaction sequence into a pseudo-interaction sequence that is then consumed by a standard sequential recommender [2509.09342]. Its central premise is that SRS captures long-term behavioral regularities from historical interactions, whereas CRS elicits immediate preference signals through natural-language interaction; CESRec treats these signals as complementary rather than separate, and operationalizes the combination through two main components: **Dual Alignment Outlier Items Masking** and **Semantic Pseudo Sequence Construction**. ## 1. Position within sequential and conversational recommendation CESRec is situated at the intersection of two recommendation paradigms with distinct strengths and limitations. In the formulation adopted by the paper, conventional SRS methods are effective at modeling long-term preferences from historical clicks or interactions, but they often rely on collaborative filtering signals and sequence patterns that do not adequately capture changing or immediate interests. CRS, by contrast, is effective at eliciting real-time user intent through dialogue, but typically does not exploit the user’s historical interaction sequence in a comparably direct way [2509.09342]. The framework is motivated by the observation that conversational signals should affect the sequence representation itself rather than merely serve as an auxiliary signal outside the recommender. When a user expresses a preference such as disliking films directed by one director and preferring those by another, CESRec interprets that feedback as evidence that the historical sequence, as seen by the recommender, should be updated. This shifts the role of conversation from side-channel preference elicitation to direct sequence refinement. A common misconception is to regard CESRec as a new standalone recommender backbone. The paper instead presents it as explicitly **model-agnostic**: it is designed to be attached to existing strong SRS models, including **SASRec**, and also to **LLM-based recommenders like LLaRA**. In this sense, CESRec is a framework for sequence transformation and preference injection rather than a replacement for sequential recommendation infrastructure. ## 2. Formal setup and target prediction problem The paper follows the standard sequential recommendation setup. For a user \(u \in \mathcal{U}\), the historical interaction sequence is \[ \mathcal{I}(u) = \{v^{(u)}_1, v^{(u)}_2, \dots, v^{(u)}_{N_u}\}, \] and the task is to predict the next item with which the user will interact [2509.09342]. CESRec preserves this objective but changes the effective input to the sequential recommender. Rather than predicting from the raw historical sequence alone, the framework constructs a refined pseudo-interaction sequence informed by dialogue. The final recommendation is produced as \[ v^{(u)}_{N_u+1}=\text{SRS}(I_{\text{pseudo}(u)}). \] This formulation is significant because it does not require a separate conversational scoring module to override or post-process the sequential model. Instead, the conversational signal is embedded into the representation of user history itself. The paper also emphasizes that historical sequences often contain **outlier items**: interactions that are noisy, transient, or otherwise misaligned with the user’s core preferences. Such items can distort sequence reconstruction. CESRec therefore treats the prediction problem as depending on two transformations of the original history: first, removal or masking of items that deviate from core preferences; second, reconstruction of the sequence using conversational feedback. ## 3. Framework architecture and end-to-end pipeline CESRec consists of two main components: **Dual Alignment Outlier Items Masking** and **Semantic Pseudo Sequence Construction** [2509.09342]. The pipeline proceeds in the following order: 1. Start from the original historical interaction sequence \(I(u)\). 2. Use dual alignment to detect and mask outlier items, producing a cleaned sequence \(I'(u)\). 3. Obtain user conversational feedback about a recommended item. 4. Feed \(I'(u)\) and the feedback into an LLM-based constructor. 5. Generate a pseudo-interaction sequence \(I_{\text{pseudo}(u)}\). 6. Feed \(I_{\text{pseudo}(u)}\) into the underlying sequential recommender to produce the final recommendation. This architecture is notable for separating **noise suppression** from **preference injection**. The first stage is intended to prevent misleading historical items from influencing the second stage; the second stage then edits the cleaned history so that the sequence reflects both long-term and real-time preferences. The framework’s model-agnostic character is operational rather than merely rhetorical. The paper applies CESRec to two different backbones, **SASRec** and **LLaRA**, indicating that the pseudo-sequence can serve as an intermediate representation for both conventional sequential recommenders and LLM-based recommenders. This suggests a modular design in which CESRec acts as a front-end sequence refinement layer. ## 4. Dual alignment outlier items masking The outlier masking module is designed to identify items in the historical sequence that are weakly aligned with the user’s core preferences. For an item \(v_i^{(u)}\) with content \(c_i\), CESRec first extracts a semantic embedding using an LLM: \[ e_i^{LLM} = \text{Extractor}(c_i), \] where the output of the last hidden layer is used as the semantic representation [2509.09342]. Because semantic embeddings alone do not preserve the collaborative structure of recommendation space, CESRec introduces a trainable adapter that aligns LLM-derived semantics with collaborative representations. The aligned embedding is written as \[ e_i^{\text{hybrid}} = \text{Adapter}(\theta_{collab}; e_i^{LLM}), \] and the appendix gives the adapter explicitly as an MLP: \[ \begin{split} \mathbf{e}_i^{\text{hybrid}} &= \text{Adapter} (\mathbf{e}_i^{\text{LLM}}) \\ &= W_2 \cdot \text{GELU}(W_1 \cdot \mathbf{e}_i^{\text{LLM}} + b_1) + b_2. \end{split} \] The adapter is trained with the alignment loss \[ L_{\text{align}} = \| \mathbf{e}_i^{\text{hybrid}} - \mathbf{e}_i^{\text{collab}} \|_2^2, \] so that the resulting representation fuses semantic information from the LLM with collaborative signals from the recommender. After obtaining hybrid item embeddings for the full sequence, CESRec computes a user representation by mean pooling: \[ u^{\text{hybrid}} = \text{Fuse}(\{e_1^{\text{hybrid}}, e_2^{\text{hybrid}}, \dots, e_{N_u}^{\text{hybrid}}\}), \] where \(\text{Fuse}(\cdot)\) is mean pooling. Each item then receives a similarity score \[ s_i = \text{Similarity}(e_i^{\text{hybrid}}, u^{\text{hybrid}}), \] with cosine similarity used in the main method. Items with the lowest similarity are treated as outliers, and the top \(k\) lowest-similarity items are masked: \[ I(u)^\prime= \text{Dual-Alignment}(I(u)), \] with \[ I(u)^\prime = \{v^{(u)}_1, \dots, v^{(u)}_{N_u-k}, \hat{v}^{(u)}_1, \dots, \hat{v}^{(u)}_k\}. \] In the main experiments, the paper reports masking one item, while additional analysis examines different numbers of masked items. The appendix compares cosine similarity with Euclidean distance and reports that cosine similarity performs better for identifying outliers and improving recommendation quality. A plausible implication is that angular alignment in the hybrid representation is more useful than raw distance for distinguishing core-preference items from anomalous ones. ## 5. Semantic pseudo interaction construction The pseudo-sequence constructor is the mechanism through which conversational feedback is translated into a modified history. CESRec first uses an SRS to recommend an item \(v_{rec}^{(u)}\) from the current sequence and then collects natural-language feedback about the recommended item’s attributes: \[ \text{feedback}=\text{User-Interaction}(v_{rec}^{(u)}, Attr_{\text{target}}). \] A trained LLM, referred to as the **Constructor**, then rewrites the masked sequence \(I'(u)\) into a pseudo-interaction sequence: \[ I_{\text{pseudo}(u)}=\text{Constructor}(I'(u), \text{feedback}). \] The intended result is a sequence that reflects both the user’s long-term preference encoded in historical behavior and the user’s real-time preference expressed in dialogue [2509.09342]. The training objective for the constructor is posed as a sequence prediction problem: \[ \mathcal{L}_{\text{seq}} = -\sum_{t=1}^{|I_{pseudo}^*(u)|} \log P_\Psi\big(v_t^* \mid v_{